Sei sulla pagina 1di 89

SCDL – 4th Semester – Data Mining

LIST OF ATTEMPTED QUESTIONS AND ANSWERS

Page 1 of 89
SCDL – 4th Semester – Data Mining

Select The Blank


Question Semantic integration of ________ genome database is the important task of DNA analysis.

Correct Heterogeneous and distributed


Answer
Your Answer Heterogeneous and distributed

Multiple Choice Single Answer


Question Main advantage of following which method is it's fast processing?

Correct Grid based


Answer
Your Answer Partioning based

Select The Blank


Question With the widespread option of ________ real-time connection is viable for data
warehouse.
Correct TCP/IP
Answer
Your Answer HTTP

Select The Blank


Question ________ are responsible for running queries and reports against data warehouse tables.

Correct End users


Answer
Your Answer End users

Multiple Choice Multiple Answer


Question Advantages of Wavelet transformation for clustering are :-

Correct Unsupervised clustering , Detection of cluster for accuracy , Clustering is fast


Answer
Your Answer Unsupervised clustering , Clustering is fast , Decomposition of cluster for accuracy

Multiple Choice Single Answer


Question Query tool is meant for :-

Correct Data acquisition


Answer
Your Answer Information delivery

Multiple Choice Single Answer


Question Which of the following function involves data cleaning, data standardizing and
summarizing?
Correct Transforming data
Answer
Your Answer Storing data

Page 2 of 89
SCDL – 4th Semester – Data Mining

LIST OF ATTEMPTED QUESTIONS AND ANSWERS

Page 3 of 89
SCDL – 4th Semester – Data Mining

True/False
Question A distinguishing feature of Clementine is its object oriented extended module interface.

Correct True
Answer
Your Answer True

Select The Blank


Question Creating ________is violation of Normalization principles.

Correct Array
Answer
Your Answer Array

True/False
Question Data Mining refers to extracting knowledge from larger amount of data.

Correct True
Answer
Your Answer True

Multiple Choice Single Answer


Question Which of the following of Grid based clustering method explorates statistical information?

Correct STING
Answer
Your Answer CLIQUE

Multiple Choice Multiple Answer


Question The different definitions of metadata are :-

Correct Data about data , Catalog of data , Data warehouse roadmap


Answer
Your Answer Catalog of data , Data warehouse roadmap , Brain of data

Select The Blank


Question In ________ type smoothing, minimum and maximum values in given bin are identified as
bin boundaries.
Correct Smoothing by bin boundaries
Answer
Your Answer Smoothing by medians

Multiple Choice Single Answer


Question Query tool is meant for :-

Correct Data acquisition


Answer
Your Answer Information delivery

Page 4 of 89
SCDL – 4th Semester – Data Mining

LIST OF ATTEMPTED QUESTIONS AND ANSWERS

Page 5 of 89
SCDL – 4th Semester – Data Mining

Multiple Choice Multiple Answer


Question Metadata is essential for IT for :-

Correct Source data structures , Data summarization


Answer
Your Answer Web enabling , Source data structures , Data summarization

Multiple Choice Multiple Answer


Question Financial data called for banking and financial industry are often relatively :-

Correct Complete , Reliable , High Quality


Answer
Your Answer Complete , Reliable , Correct

Select The Blank


Question ________ option of warehouse architecture provides incremental growth.

Correct Cluster
Answer
Your Answer Cluster

Match The Following


Question Correct Answer Your Answer

Operating systems compatibility Security, reliability, availability Security, reliability, availability

Data Acquisition Data Extraction, Transformation, Data Extraction, Transformation,


clensing, integration clensing, integration
Data Storage Data loading , Archiving Data loading , Archiving

Information Delivery Report generation, query Report generation, query processing


processing and complex analysis and complex analysis

True/False
Question A cluster is a collection of similar data objects in same cluster and disimilar to objects in
another cluster.
Correct True
Answer
Your Answer True

Multiple Choice Single Answer


Question Which of the following method creates copies of data in distributed environment?

Correct Replication
Answer
Your Answer Replication

True/False
Question Data cube stores multidimensional aggregate information.

Page 6 of 89
SCDL – 4th Semester – Data Mining

LIST OF ATTEMPTED QUESTIONS AND ANSWERS

Page 7 of 89
SCDL – 4th Semester – Data Mining

Multiple Choice Single Answer


Question Deviation based outlier detection identifes outliers by :-

Correct Answer Examining character of objects in groups

Your Answer Examining character of objects in groups

Select The Blank


Question ________ component of warehouse is responsible for coordinating services and
activities within the data warehouse.
Correct Answer Management and Control

Your Answer Management and Control

True/False
Question Sequential pattern analysis and similarity search techniques have been developed in
data mining.
Correct Answer True

Your Answer True

True/False
Question A distinct feature of DB Miner is its data cube based online analytical mining.

Correct Answer True

Your Answer True

Select The Blank


Question ________ is the user who has system access privileges but no database administration
privileges as well as not for table and views.
Correct Answer Network administrator

Your Answer Network administrator

Select The Blank


Question For operational system, the stored data contains ________values.

Correct Answer Current data

Your Answer Current data

True/False
Question Intelligent miner is an IBM data mining product.

Correct Answer True

Your Answer True

Page 8 of 89
SCDL – 4th Semester – Data Mining

LIST OF ATTEMPTED QUESTIONS AND ANSWERS

Page 9 of 89
SCDL – 4th Semester – Data Mining

Multiple Choice Single Answer


Question Which type of Grid clustering depends on the granularity of lowest level of grid structure?

Correct STING
Answer
Your Answer OPTICS

Multiple Choice Single Answer


Question Which of the following option of data extraction is known as application assisted data
capture?
Correct Capture in source application
Answer
Your Answer Capture by comparing files

True/False
Question Moving data into staging area and performing data transformation function is a part of data
acquisition.
Correct True
Answer
Your Answer True

Multiple Choice Multiple Answer


Question The objective for physical design of data warehouse are :-

Correct Improve performance , Ensure scalability , Manage store


Answer
Your Answer Improve performance , Ensure scalability , Manage database

Multiple Choice Multiple Answer


Question User must have proper access to metadata for performing responsibilities of :-

Correct Design , Administration


Answer
Your Answer Design , Administration , Management

Multiple Choice Multiple Answer


Question In Intelligent miner the data mining product provides data mining algorithm including

Correct Association , Classification , Regression


Answer
Your Answer Association , Regression , Aggregation

Multiple Choice Single Answer


Question The big difference between data warehouse and any operational system is its :-

Correct Usage
Answer
Your Answer Organization

Page 10 of 89
SCDL – 4th Semester – Data Mining

LIST OF ATTEMPTED QUESTIONS AND ANSWERS

Page 11 of 89
SCDL – 4th Semester – Data Mining

Select The Blank


Question ________ method of regression is useful when errors fails to satisfy normal conditions.

Correct Robust
Answer
Your Answer Robust

True/False
Question Data classification is two step process in which first step includes classfication of model
and in second step model describes set of data.
Correct False
Answer
Your Answer True

True/False
Question Data cleansing means removing noisy and inconsistent data.

Correct True
Answer
Your Answer True

Multiple Choice Multiple Answer


Question Following factors play important role in financial analysis :-

Correct Data warehouse , Data cubes , Outliner analysis


Answer
Your Answer Data warehouse , Data cubes , Data accuracy

Multiple Choice Single Answer


Question Data matrix is :-

Correct Object by variable structure


Answer
Your Answer Object by object structure

Multiple Choice Multiple Answer


Question The dimensions of spatial data cube are :-

Correct Non- spatial dimension , Spatial to non spatial , Spatial to spatial


Answer
Your Answer Non- spatial dimension , Spatial to non spatial , Spatial to spatial

Multiple Choice Single Answer


Question Query tool is meant for :-

Correct Data acquisition


Answer
Your Answer Data acquisition

Page 12 of 89
SCDL – 4th Semester – Data Mining

LIST OF ATTEMPTED QUESTIONS AND ANSWERS

Page 13 of 89
SCDL – 4th Semester – Data Mining

Multiple Choice Single Answer


Question The technique of data clustering facilitates :-

Correct Serial access


Answer
Your Answer Indexed access

Select The Blank


Question In ________ type smoothing, minimum and maximum values in given bin are identified as
bin boundaries.
Correct Smoothing by bin boundaries
Answer
Your Answer Smoothing by bin boundaries

Multiple Choice Multiple Answer


Question The ways of Intra query parallelization are :-

Correct Horizontal parallelization , Vertical Parallelization , Hybrid parallelization


Answer
Your Answer Vertical Parallelization , Homogenous parallelization

Select The Blank


Question ________ technique is the statistical technique for analyzing data.

Correct Time series


Answer
Your Answer Time series

True/False
Question One of the most important search problem in genetic analysis is similarity search and
comparison among DNA sequence.
Correct True
Answer
Your Answer True

Multiple Choice Multiple Answer


Question User must have proper access to metadata for performing responsibilities of :-

Correct Design , Administration


Answer
Your Answer Administration , Management , Accessing

Multiple Choice Single Answer


Question Association rules mining is based on :-

Correct Clustering and Employing rules for classification


Answer
Your Answer Clustering and Employing rules for classification

Page 14 of 89
SCDL – 4th Semester – Data Mining

LIST OF ATTEMPTED QUESTIONS AND ANSWERS

Page 15 of 89
SCDL – 4th Semester – Data Mining

Multiple Choice Multiple Answer


Question DNA sequences are comprised of :-

Correct Gaunine , Thymine , Adenine


Answer
Your Answer Gaunine , Thymine , Adenine , Cytocine

Multiple Choice Multiple Answer


Question Source Data Component may be grouped into following categories :-

Correct Production Data , Internal External Data


Answer
Your Answer Production Data , Internal External Data

True/False
Question Loan payment prediction and customer credit analysis are critical to business of bank.

Correct True
Answer
Your Answer True

Multiple Choice Multiple Answer


Question Preprocessing steps of data in order to help improve accuracy, efficiency and scalability of
classification & prediction are :-
Correct Data Cleaning , Relevance Analysis , Data Transformation
Answer
Your Answer Data Cleaning , Relevance Analysis , Data Transformation

Multiple Choice Single Answer


Question The big difference between data warehouse and any operational system is its :-

Correct Usage
Answer
Your Answer Usage

True/False
Question Data cleansing means removing noisy and inconsistent data.

Correct True
Answer
Your Answer True

True/False
Question Moving data into staging area and performing data transformation function is a part of data
acquisition.
Correct True
Answer
Your Answer True

Page 16 of 89
SCDL – 4th Semester – Data Mining

LIST OF ATTEMPTED QUESTIONS AND ANSWERS

Page 17 of 89
SCDL – 4th Semester – Data Mining

True/False
Question Data cube stores multidimensional aggregate information.

Correct True
Answer
Your Answer True

Select The Blank


Question ________ is a summarization of general characteristics or features of a target class of data.

Correct Data Characterization


Answer
Your Answer Data Generalization

Multiple Choice Single Answer


Question The pilot which is useful for user and project team both as it touches all important functions
is :-
Correct Expanded seed pilot
Answer
Your Answer User tool appreciation pilot

Multiple Choice Single Answer


Question Which of the following technique involves placing and managing related units of data in
same physical block of storage
Correct Clustering
Answer
Your Answer Clustering

Multiple Choice Multiple Answer


Question History of metadata includes :-

Correct Changes to source system , Data extraction methods , Data transformation algorithm
Answer
Your Answer Changes to source system , Data extraction methods

Multiple Choice Single Answer


Question Which of the following approach requires more computation?

Correct Filter approach


Answer
Your Answer Filter approach

True/False
Question The substantial part of historical data comes form antiquated legacy system.

Correct True
Answer
Your Answer True

Page 18 of 89
SCDL – 4th Semester – Data Mining

LIST OF ATTEMPTED QUESTIONS AND ANSWERS

Page 19 of 89
SCDL – 4th Semester – Data Mining

True/False
Question Matching the choice of DBMS with selected server hardware is not important for
warehouse.
Correct Answer False

Your Answer False

Match The Following


Question Correct Answer Your Answer

Metadata Roadmap for user Roadmap for user

Data storage Data management Data management

Data staging Workbench for data Workbench for data

Data Mining Knowledge discovery Knowledge discovery

True/False
Question Database systems, data warehouse system and world wide web have become
mainstream information system.
Correct Answer True

Your Answer True

Multiple Choice Single Answer


Question Bitmapped indexes are more suitable for data warehouse environment than for an
OLTP system
Correct Answer Bitmapped index

Your Answer Bitmapped index

Multiple Choice Single Answer


Question The big difference between data warehouse and any operational system is its :-

Correct Answer Usage

Your Answer Usage

Multiple Choice Single Answer


Question One major effort within data transformation is :-

Correct Answer Improvement of data quality

Your Answer Analysis of data quality

Multiple Choice Multiple Answer


Question Advantages of Wavelet transformation for clustering are :-

Page 20 of 89
SCDL – 4th Semester – Data Mining

LIST OF ATTEMPTED QUESTIONS AND ANSWERS

Select The Blank


Question: ________ function of data staging component involves many forms of combining
pieces of data from different sources.
Correct Answer: Data Transformation
Your Answer: Data Transformation

Multiple Choice Multiple Answer


Question: The Main areas of Data Warehouse are :-
Correct Answer: Data acquisition , Data Storage , Information Delivery
Your Answer: Data acquisition , Data Storage , Information Delivery

Select The Blank


Question: Data cleansing and ________ methods of data mining helps in integration of genetic
data and construction of warehouse for genetic data analysis.
Correct Answer: Integration
Your Answer: Integration

Multiple Choice Multiple Answer


Question: The dimensions of spatial data cube are :-
Correct Answer: Non- spatial dimension , Spatial to non spatial , Spatial to spatial
Your Answer: Non- spatial dimension , Spatial to non spatial , Spatial to spatial

Multiple Choice Single Answer


Question: In data reduction, the cluster representations of data are used to :-
Correct Answer: Replace data
Your Answer: Represent actual data

Multiple Choice Multiple Answer


Question: Distinguishing characteristics of data warehouse architecture are :-
Correct Answer: Different Objective Scope , Data Content , Flexible and Dynamic
Your Answer: Different Objective Scope , Complete Analysis and Quick Response , Flexible and
Dynamic

Select The Blank


Question: In data warehouse architecture, the ________ component interleaves with and
connects other components.
Correct Answer: Metadata
Your Answer: Metadata

Multiple Choice Multiple Answer


Question: Methods for outlier detection are categorised into following approaches :-
Correct Answer: Statistical , Distance based , Deviation based
Your Answer: Statistical , Distance based , Deviation based

True/False
Question: Metadata describes all the pertinent aspects of the data in data warehouse.
Correct Answer: True
Your Answer: True

Multiple Choice Multiple Answer


Question: Financial data called for banking and financial industry are often relatively :-

Page 21 of 89
SCDL – 4th Semester – Data Mining

Correct Answer: Complete , Reliable , High Quality


Your Answer: Complete , Reliable , High Quality

Multiple Choice Multiple Answer


Question: Classification and Prediction have following applications :-
Correct Answer: Credit approval , Medical Diagnosis , Performance Prediction
Your Answer: Credit approval , Medical Diagnosis , Performance Prediction

True/False
Question: Data Integration means multiple resourses may be combined.
Correct Answer: True
Your Answer: True

Select The Blank


Question: ________ can store aggregate and detail data at varying levels of resolution or
abstraction.
Correct Answer: Index tree
Your Answer: Multidimensional index tree

True/False
Question: Moving data into staging area and performing data transformation function is a part of
data acquisition.
Correct Answer: True
Your Answer: True

True/False
Question: Lower the level of detail, finer the data granularity.
Correct Answer: True
Your Answer: True

Select The Blank


Question: ________ is an alternative aggolomerative hierarchical clustering algorithm.
Correct Answer: ROCK
Your Answer: ROCK

Multiple Choice Single Answer


Question: Real world databases are highly susceptible to noisy, missing and inconsistent data
due to :-
Correct Answer: Huge size of data
Your Answer: Huge size of data

Multiple Choice Single Answer


Question: Bayes Theorem is :-
Correct Answer: P(H|X)=P(X|H)(P)/P(X)
Your Answer: P(H|X)=P(X|H)(P)/P(X)

Multiple Choice Multiple Answer


Question: Data mining Functionalities are :-
Correct Answer: Charactrization and Discrimination , Association Analysis , Cluster Analysis
Your Answer: Charactrization and Discrimination , Association Analysis , Cluster Analysis

Select The Blank


Question: ________ does not handle categorical attributes.
Correct Answer: CURE
Your Answer: ROCK

Page 22 of 89
SCDL – 4th Semester – Data Mining

Multiple Choice Single Answer


Question: Classification rules are extracted from
Correct Answer: Decision Tree
Your Answer: Decision Tree

Select The Blank


Question: The ________ record is one-to-many relationship with corresponding fact table record.
Correct Answer: Dimension tables
Your Answer: Dimension tables

True/False
Question: In Database system multidimensional index trees are primarily used for providing fast
data access.
Correct Answer: True
Your Answer: True

Match The Following


Question Correct Answer Your Answer
Data Mining Knowledge discovery Knowledge discovery
Metadata Roadmap for user Roadmap for user
Data storage Data management Data management
Data staging Workbench for data Workbench for data

True/False
Question: COBWEB is a method of incremental conceptual clustering.
Correct Answer: True
Your Answer: True

Multiple Choice Multiple Answer


Question: The different analysis tools which are useful to detect unusual patterns such as large
amount of cash flow at certain period by certain group of people are :-
Correct Answer: Linkage analysis tool , Outlier analysis tool , Sequential pattern analysis tool
Your Answer: Linkage analysis tool , Outlier analysis tool , Sequential pattern analysis tool

Match The Following


Question Correct Answer Your Answer
Disparate data Production data Production data
Non volatile data Query and analysis Query and analysis
Data granularity Level of detail Level of detail
Data from external External data External data
source

Multiple Choice Multiple Answer


Question: Advantages of Wavelet transformation for clustering are :-
Correct Answer: Unsupervised clustering , Detection of cluster for accuracy , Clustering is fast
Your Answer: Unsupervised clustering , Detection of cluster for accuracy , Clustering is fast

Multiple Choice Single Answer


Question: Association rules mining is based on :-
Correct Answer: Clustering and Employing rules for classification
Your Answer: Clustering and Employing rules for classification

Multiple Choice Single Answer


Question: Data can be smoothed by filling the data to function such as :-
Correct Answer: Regression
Your Answer: Regression

Page 23 of 89
SCDL – 4th Semester – Data Mining

Multiple Choice Multiple Answer


Question: In physical design of data warehouse administration provides features like :-
Correct Answer: Support backup and recovery , Query processing , Avoiding reorganizing of
tables
Your Answer: Avoiding reorganizing of tables , Support backup and recovery , Query processing

True/False
Question: MDDBMS stands for - Multilevel Database Management System.
Correct Answer: False
Your Answer: False

Multiple Choice Single Answer


Question: Effect of one attibute value on a given class is independent of values of other attibute
is called
Correct Answer: Value independence
Your Answer: Value independence

Multiple Choice Multiple Answer


Question: When you use tool for design and development, following things take place with
metadata :-
Correct Answer: Metadata is no longer passive document , Metadata takes part in process ,
Metadata aids in automation of data warehouse process
Your Answer: Metadata is no longer passive document , Metadata takes part in process ,
Metadata aids in automation of data warehouse process

Multiple Choice Single Answer


Question: Data partitioning, data clustering are the techniques for :-
Correct Answer: Performance enhancement
Your Answer: Performance enhancement

Multiple Choice Multiple Answer


Question: Knowledge discovery process includes :-
Correct Answer: Data Cleaning , Data Intergration , Data Selectin
Your Answer: Data Cleaning , Data Intergration , Data Selectin

Multiple Choice Single Answer


Question: Query tool is meant for :-
Correct Answer: Data acquisition
Your Answer: Data acquisition

Multiple Choice Multiple Answer


Question: The functions of data acquisition are :-
Correct Answer: Data Extraction , Data Transformation
Your Answer: Data Extraction , Data Transformation

Select The Blank


Question: ________ databases are one of the most poplularly available and rich information
repositories.
Correct Answer: Relational
Your Answer: Relational

True/False
Question: From a Dataware house perspective data mining canbe viewed as an advanced stage
of Online Analytical Programming.
Correct Answer: True

Page 24 of 89
SCDL – 4th Semester – Data Mining

Your Answer: True

Multiple Choice Multiple Answer


Question: Which of the following clustering analysis method uses multiresolution approach?
Correct Answer: STING , Wave Cluster
Your Answer: STING , Wave Cluster

True/False
Question: The Structure that brings all the components together is known as Architecture.
Correct Answer: True
Your Answer: True

Select The Blank


Question: Human being have around ________ gene.
Correct Answer: 100000
Your Answer: 100000

Select The Blank


Question: ________ is the method used to predict the value of response variable from one to
more variables.
Correct Answer: Regression
Your Answer: Regression

Multiple Choice Single Answer


Question: Which of the following type executes query operations in pipeline manner?
Correct Answer: Vertical parallelism
Your Answer: Vertical parallelism

True/False
Question: Data cleansing means removing noisy and inconsistent data.
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: When DDL statements are created using database software, so to create an index
system creates :-
Correct Answer: B-Tree index
Your Answer: B-Tree index

LIST OF ATTEMPTED QUESTIONS AND ANSWERS

True/False
Question: Architecture comes first, tools follows it.
Correct Answer: True
Your Answer: True

Multiple Choice Multiple Answer


Question: Following are the theories for the basis of data mining :-
Correct Answer: Pattern discovery , Probability theory , Microeconomic view
Your Answer: Pattern discovery , Probability theory , Microeconomic view

True/False
Question: Data preprocessing is an important step in knowledge discovery process.
Correct Answer: True
Your Answer: True

Page 25 of 89
SCDL – 4th Semester – Data Mining

True/False
Question: A distinguishing feature of Clementine is its object oriented extended module
interface.
Correct Answer: True
Your Answer: True

Multiple Choice Multiple Answer


Question: The Architecture defines :-
Correct Answer: Measurements , Standard , General Design
Your Answer: Measurements , Standard , Standard Techniques

Select The Blank


Question: ________ technique contribute to machine learning, neural network, association
mining, sequential pattern mining.
Correct Answer: Pattern discovery
Your Answer: Pattern discovery

Match The Following


Question Correct Answer Your Answer
Classification tool To filter unrelated attributes To characterize unusual access
sequence
Clustering tool To group different cases Transaction activity using graph
Data visualization Transaction activity using To group different cases
Tool graph
Linkage analysis tool To identify links To identify links

Multiple Choice Multiple Answer


Question: Data processing techniques are :-
Correct Answer: Cleansing , Integration , Transformation
Your Answer: Cleansing , Integration , Transformation

Select The Blank


Question: Creating ________is violation of Normalization principles.
Correct Answer: Array
Your Answer: Cluster

Multiple Choice Multiple Answer


Question: Building blocks of Data Warehouse are :-
Correct Answer: Source Data , Data Staging , Management and Control
Your Answer: Source Data , Data Staging , Data Manager

Multiple Choice Single Answer


Question: OPTICS regarding clustering stands for :-
Correct Answer: Ordering Points to identify the clustering Structure
Your Answer: Ordering Points to identify the clustering Structure

Select The Blank


Question: ________ that unable massive quantities of data to be transported from one
platform to another.
Correct Answer: Data ports
Your Answer: Data ports

True/False
Question: Sequential pattern analysis and similarity search techniques have been developed in
data mining.

Page 26 of 89
SCDL – 4th Semester – Data Mining

Correct Answer: True


Your Answer: True

Multiple Choice Single Answer


Question: The stored values of an attribute represents the value of attribute at this moment of
time is :-
Correct Answer: Current value
Your Answer: Value of attribute

Match The Following


Question Correct Answer Your Answer
Data loading tool Primary key generation Bulk extraction for full refresh

Data modeling tool Reverse Engineering Reverse Engineering capabilities


Capabilities
Data Extraction tool Bulk extraction for full Default values
refresh
Data transformation Default values Primary key generation
tool

True/False
Question: Audio data mining can be an interesting alternative to visual mining.
Correct Answer: True
Your Answer: True

Select The Blank


Question: Most of the warehouses employ ________ database Management System.
Correct Answer: Relational
Your Answer: Hierarchical

Multiple Choice Single Answer


Question: Which from the following are special programs that are stored on database and fired
when certain predefined action occurs?
Correct Answer: Triggers
Your Answer: Events

Multiple Choice Multiple Answer


Question: For processing metadata in informal delivery area, data can be referred back for :-
Correct Answer: Data structure , Data transformation , Source data configuration
Your Answer: Source data configuration , Data structure , Data transformation

Multiple Choice Multiple Answer


Question: Following are the types of normalization :-
Correct Answer: Min-Max Normalization , Z-score normalization , Normalization by scaling
Your Answer: Min-Max Normalization , Z-score normalization , Normalization by scaling

Multiple Choice Single Answer


Question: Following clustering method is classified as being agglomerative or divisive :-
Correct Answer: Grid based
Your Answer: Partioning based

Multiple Choice Single Answer


Question: The big difference between data warehouse and any operational system is its :-
Correct Answer: Usage
Your Answer: Structure

Page 27 of 89
SCDL – 4th Semester – Data Mining

Multiple Choice Multiple Answer


Question: Following are the data movement options in data warehouse :-
Correct Answer: Shared disk , Mass data transmission , Real time connection
Your Answer: Shared disk , Mass data transmission , Real time connection

True/False
Question: Data Mining refers to extracting knowledge from larger amount of data.
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: Main advantage of following which method is it's fast processing?
Correct Answer: Grid based
Your Answer: Density based

Select The Blank


Question: Indexed ________ engines search index,web pages and build huge keyword based
indices which help to search sets of web pages containing certain keywords
Correct Answer: Web Search
Your Answer: Web Search

Multiple Choice Multiple Answer


Question: Data base miner provides multiple data mining algorithms including :-
Correct Answer: Discovery driven OLAP analysis , Association , Classification
Your Answer: Discovery driven OLAP analysis , Association , Regression

Select The Blank


Question: ________ method of regression is useful when errors fails to satisfy normal
conditions.
Correct Answer: Robust
Your Answer: Non parametric

True/False
Question: All data extraction, transformation, integration and staging jobs run on selected
hardware under chosen operating system.
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: Deviation based outlier detection identifes outliers by :-
Correct Answer: Examining character of objects in groups
Your Answer: Examining character of objects in groups

Select The Blank


Question: It is good practice to drop ________ before initial load.
Correct Answer: Index
Your Answer: Index

Select The Blank


Question: Most of DBMS have ________ index techniques as default index techniques.
Correct Answer: B-Tree
Your Answer: B-Tree

Select The Blank


Question: In ________ duplicate sub trees exist within the tree.
Correct Answer: Repetition

Page 28 of 89
SCDL – 4th Semester – Data Mining

Your Answer: Fragmentation

Multiple Choice Single Answer


Question: Which is the typical example of Grid based clustering method
Correct Answer: STING
Your Answer: DBSCAN

True/False
Question: In the data acquisition area, the data flow begins at the data sources and pauses at
staging area.
Correct Answer: True
Your Answer: True

Multiple Choice Multiple Answer


Question: In data storage area , DBA uses metadata for processes of :-
Correct Answer: Backup , Recovery , Tuning Database
Your Answer: Backup , Recovery

True/False
Question: Descriptive mining takes perform ingerence on current data which predictive mining
characterize the general properties of data in database
Correct Answer: False
Your Answer: True

Select The Blank


Question: When data block contains excessive amount of free space, performance ________
Correct Answer: Degenerates
Your Answer: Degenerates

Select The Blank


Question: ________ platform is the platform on which the data warehouse DBMS runs and
database exist.
Correct Answer: Data storage
Your Answer: Legacy

Multiple Choice Multiple Answer


Question: Data integration means :-
Correct Answer: Integrating database , Integrating cubes , Integrating files
Your Answer: Integrating database , Integrating cubes , Integrating files

Multiple Choice Single Answer


Question: Which technique analyze experimental data?
Correct Answer: Analysis of variance
Your Answer: Analysis of variance

True/False
Question: Smoothing by bin means each value in bin is replaced by the mean value of the
bucket.
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: Maintenance of cache consistency is the limitation of :-
Correct Answer: MPP
Your Answer: SMP

Page 29 of 89
SCDL – 4th Semester – Data Mining

Multiple Choice Multiple Answer


Question: Substantial portion of Business metadata originates from :-
Correct Answer: Textual documents , Spreadsheets , Business rules
Your Answer: Textual documents , Spreadsheets , Business rules

Multiple Choice Single Answer


Question: Redundancies can be deleted by :-
Correct Answer: Co-relational analysis
Your Answer: Relational analysis

Multiple Choice Single Answer


Question: Data reduction obtains a reduced representation of data set that is :-
Correct Answer: Much smaller
Your Answer: Much smaller

LIST OF ATTEMPTED QUESTIONS AND ANSWERS

Select The Blank


Question: Data cleansing and ________ methods of data mining helps in integration of genetic
data and construction of warehouse for genetic data analysis.
Correct Answer: Integration
Your Answer: Integration

Select The Blank


Question: ________ method of regression is useful when errors fails to satisfy normal
conditions.
Correct Answer: Robust
Your Answer: Robust

Multiple Choice Single Answer


Question: Bitmap index takes significantly less space than which type of index?
Correct Answer: B-Tree index
Your Answer: B-Tree index

Select The Blank


Question: ________components consists all the different ways of making the information from
the data warehouse available to the user.
Correct Answer: Information Delivery
Your Answer: Information Delivery

True/False
Question: Architecture comes first, tools follows it.
Correct Answer: True
Your Answer: True

Multiple Choice Multiple Answer


Question: The Main areas of Data Warehouse are :-
Correct Answer: Data acquisition , Data Storage , Information Delivery
Your Answer: Data acquisition , Data Storage , Information Delivery

Select The Blank


Question: ________ is density based clustering method which computes on augumented
clustering ordering for automic ordering for automatic and interactive cluster analysis
Correct Answer: DBSCAN
Your Answer: DBSCAN

Page 30 of 89
SCDL – 4th Semester – Data Mining

Match The Following


Question Correct Answer Your Answer
Load Utility High performance data High performance data loading,
loading, recovery recovery
Query Governer Abort runaway query Active data catalog/directory
Query Optimizer Parsing, optimizing query Parsing, optimizing query
Query Management Balancing extraction of query Execution and rescheduling queries

Multiple Choice Multiple Answer


Question: Source Data Component may be grouped into following categories :-
Correct Answer: Production Data , Internal External Data
Your Answer: Production Data , Internal External Data

Select The Blank


Question: ________ is the type of pilot for early delivery with broader scope and may be
integrated.
Correct Answer: Broad business pilot
Your Answer: Broad business pilot

Multiple Choice Multiple Answer


Question: The smoothing techniques are :-
Correct Answer: Binning , Clustering , Regression
Your Answer: Clustering , Regression

Multiple Choice Single Answer


Question: Which of the following data warehouse component includes dependent data marts,
special multidimensional database and full range of query and reporting facilities?
Correct Answer: Information Delivery component
Your Answer: Metadata Component

True/False
Question: The Structure that brings all the components together is known as Architecture.
Correct Answer: True
Your Answer: True

Select The Blank


Question: The technique of ________ enables concurrent input/output operations and improves
file's access performance substantially.
Correct Answer: File striping
Your Answer: File striping

True/False
Question: Management architectural component manages and controls data acquisition
functions.
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: If many indexes are needed, then on which table which option is more preferable?
Correct Answer: Splitting of tables
Your Answer: Rearranging of tables

Multiple Choice Single Answer


Question: Which of the following of Grid based clustering method explorates statistical
information?

Page 31 of 89
SCDL – 4th Semester – Data Mining

Correct Answer: STING


Your Answer: STING

Multiple Choice Single Answer


Question: Attribute construction is the part of :-
Correct Answer: Transformation
Your Answer: Aggregation

Multiple Choice Multiple Answer


Question: DNA sequences are comprised of :-
Correct Answer: Adenine , Gaunine , Thymine
Your Answer: Gaunine , Thymine , Adenine

True/False
Question: In decision tree internal nodes are denoted by ovals and leaf nodes are denoted by
rectangles
Correct Answer: False
Your Answer: False

Multiple Choice Single Answer


Question: Effect of one attibute value on a given class is independent of values of other attibute
is called
Correct Answer: Value independence
Your Answer: Value independence

Multiple Choice Single Answer


Question: Association rules mining is based on :-
Correct Answer: Clustering and Employing rules for classification
Your Answer: Clustering and Employing rules for classification

Select The Blank


Question: Most of DBMS have ________ index techniques as default index techniques.
Correct Answer: B-Tree
Your Answer: B-Tree

Match The Following


Question Correct Answer Your Answer
Disparate data Production data Production data
Non volatile data Query and analysis Query and analysis
Data granularity Level of detail Level of detail
Data from external External data External data
source

Multiple Choice Single Answer


Question: Dimensionality reduction reduces the data set size by removing :-
Correct Answer: Irrelevant attributes
Your Answer: Irrelevant attributes

Multiple Choice Multiple Answer


Question: Data reduction reduces data size by :-
Correct Answer: Aggregation , Eliminating redundant features
Your Answer: Aggregation , Eliminating redundant features , Restructuring

True/False
Question: Data integration merges data from multiple sources into coherent sources.
Correct Answer: True

Page 32 of 89
SCDL – 4th Semester – Data Mining

Your Answer: True

Multiple Choice Single Answer


Question: The option "capture in source application technique of data extraction degrades
performance of source application because :-
Correct Answer: Additional processing needs
Your Answer: Additional processing needed to capture changes on separate files

Multiple Choice Single Answer


Question: Which of the following type executes query operations in pipeline manner?
Correct Answer: Vertical parallelism
Your Answer: Vertical parallelism

Multiple Choice Single Answer


Question: Data partitioning, data clustering are the techniques for :-
Correct Answer: Performance enhancement
Your Answer: Performance enhancement

True/False
Question: COBWEB is an extension of CLASSIT for incremental clustering of contineous data.
Correct Answer: False
Your Answer: True

Multiple Choice Multiple Answer


Question: Following are the issues to consider during data integration :-
Correct Answer: Detection and resolution of data values , Schema integration , Redundancy
Your Answer: Schema integration , Redundancy , Detection and resolution of data values

Multiple Choice Single Answer


Question: Classification rules are extracted from
Correct Answer: Decision Tree
Your Answer: Decision Tree

Multiple Choice Multiple Answer


Question: Which of the following clustering analysis method uses multiresolution approach?
Correct Answer: STING , Wave Cluster
Your Answer: STING , Wave Cluster

True/False
Question: Lower the level of detail, finer the data granularity.
Correct Answer: True
Your Answer: True

Select The Blank


Question: ________ does not handle categorical attributes.
Correct Answer: CURE
Your Answer: CURE

Multiple Choice Multiple Answer


Question: When you use tool for design and development, following things take place with
metadata :-
Correct Answer: Metadata is no longer passive document , Metadata takes part in process ,
Metadata aids in automation of data warehouse process
Your Answer: Metadata is no longer passive document , Metadata takes part in process ,
Metadata aids in automation of data warehouse process

Page 33 of 89
SCDL – 4th Semester – Data Mining

Multiple Choice Single Answer


Question: Bayes Theorem is :-
Correct Answer: P(H|X)=P(X|H)(P)/P(X)
Your Answer: P(H|X)=P(X|H)(P)/P(X)

True/False
Question: Data mining is not that much powerful tool for vast data such as gene sequences in
DNA analysis.
Correct Answer: True
Your Answer: False

Multiple Choice Multiple Answer


Question: The dimensions of spatial data cube are :-
Correct Answer: Non- spatial dimension , Spatial to non spatial , Spatial to spatial
Your Answer: Non- spatial dimension , Spatial to non spatial , Spatial to spatial

True/False
Question: Easily accessible metadata is crucial for end users.
Correct Answer: True
Your Answer: True

Multiple Choice Multiple Answer


Question: Classification and Prediction have following applications :-
Correct Answer: Credit approval , Medical Diagnosis , Performance Prediction
Your Answer: Credit approval , Medical Diagnosis , Performance Prediction

True/False
Question: All data extraction, transformation, integration and staging jobs run on selected
hardware under chosen operating system.
Correct Answer: True
Your Answer: False

Select The Blank


Question: ________ databases are one of the most poplularly available and rich information
repositories.
Correct Answer: Relational
Your Answer: Relational

Multiple Choice Multiple Answer


Question: Advantages of Wavelet transformation for clustering are :-
Correct Answer: Unsupervised clustering , Detection of cluster for accuracy , Clustering is fast
Your Answer: Unsupervised clustering , Detection of cluster for accuracy , Clustering is fast

Select The Blank


Question: ________ is the platform for complex data transformation for the purpose of cleanse it
Correct Answer: Separate optimal Platform
Your Answer: Separate optimal Platform

Select The Blank


Question: ________ technique contribute to machine learning, neural network, association
mining, sequential pattern mining.
Correct Answer: Pattern discovery
Your Answer: Pattern discovery

LIST OF ATTEMPTED QUESTIONS AND ANSWERS

Page 34 of 89
SCDL – 4th Semester – Data Mining

Multiple Choice Single Answer


Question: Data matrix is :-
Correct Answer: Object by variable structure
Your Answer: Object by variable structure

Multiple Choice Multiple Answer


Question: Following are the data movement options in data warehouse :-
Correct Answer: Shared disk , Mass data transmission , Real time connection
Your Answer: Shared disk , Mass data transmission , Real time connection

Multiple Choice Single Answer


Question: In data reduction, the cluster representations of data are used to :-
Correct Answer: Replace data
Your Answer: Replace data

True/False
Question: Descriptive mining takes perform ingerence on current data which predictive mining
characterize the general properties of data in database
Correct Answer: False
Your Answer: False

Multiple Choice Single Answer


Question: For Incremental data loads the sequence is :-
Correct Answer: Triggering ->Filtering ->data extraction -> Transformation ->Integration
->cleansing
Your Answer: Triggering ->Filtering ->data extraction -> Transformation ->Integration
->cleansing

True/False
Question: COBWEB incrementally incarporates objects into classification tree.
Correct Answer: True
Your Answer: True

True/False
Question: Moving data into staging area and performing data transformation function is a part of
data acquisition.
Correct Answer: True
Your Answer: True

Select The Blank


Question: Creating ________is violation of Normalization principles.
Correct Answer: Array
Your Answer: Cluster

Multiple Choice Single Answer


Question: Which of the following method is built on Influece function?
Correct Answer: DENCLUE
Your Answer: STING

Multiple Choice Single Answer


Question: Which of the following methods for regression is used on sparse data :-
Correct Answer: Regression and log-linear model
Your Answer: Regression and log-linear model

Multiple Choice Multiple Answer

Page 35 of 89
SCDL – 4th Semester – Data Mining

Question: Building blocks of Data Warehouse are :-


Correct Answer: Source Data , Data Staging , Management and Control
Your Answer: Source Data , Data Staging , Management and Control

Multiple Choice Multiple Answer


Question: Metadata in a data warehouse falls into following categories :-
Correct Answer: Operational Metadata , Extraction and Transformation metadata , End-user
Metadata
Your Answer: Operational Metadata , Extraction and Transformation metadata , End-user
Metadata

Multiple Choice Single Answer


Question: SMP stands for :-
Correct Answer: Symmetric Multiprocessing
Your Answer: Symmetric Multiprocessing

Multiple Choice Multiple Answer


Question: Partitioning in physical design of data warehouse consists of :-
Correct Answer: Fact tables and dimension tables , Number of partitions for each table , Criteria
for dividing table
Your Answer: Fact tables and dimension tables , Number of partitions for each table , Criteria for
dividing table

True/False
Question: Data updates are common place in an operational database.
Correct Answer: True
Your Answer: True

True/False
Question: A cluster is a collection of similar data objects in same cluster and disimilar to objects
in another cluster.
Correct Answer: True
Your Answer: True

Multiple Choice Multiple Answer


Question: The functional areas of metadata are :-
Correct Answer: Data Acquisition , Data storage , Information delivery
Your Answer: Data transformation , Data Acquisition , Information delivery

Select The Blank


Question: ________ regression involves finding the best time to fit two variables.
Correct Answer: Linear
Your Answer: Linear

Match The Following


Question Correct Answer Your Answer
Administration Providing support for all Support for System administration
DBA functions
Extensibility Hybrid Extension to OLAP Hybrid Extension to OLTP database
database
Portability Across platform Across platform
Query tool APIs For tools from loading Providing support for all DBA vendors
functions

Multiple Choice Single Answer


Question: Which of the following type of processing provides high concurrency?

Page 36 of 89
SCDL – 4th Semester – Data Mining

Correct Answer: SMP


Your Answer: ccNUMA

Select The Blank


Question: Semantic integration of ________ genome database is the important task of DNA
analysis.
Correct Answer: Heterogeneous and distributed
Your Answer: Heterogeneous and distributed

True/False
Question: To remove noise from data is called as Smoothing.
Correct Answer: True
Your Answer: True

Match The Following


Question Correct Answer Your Answer
Data Mining Knowledge discovery Knowledge discovery
Metadata Roadmap for user Roadmap for user
Data storage Data management Data management
Data staging Workbench for data Workbench for data

Multiple Choice Multiple Answer


Question: Knowledge discovery process includes :-
Correct Answer: Data Cleaning , Data Intergration , Data Selectin
Your Answer: Data Cleaning , Data Intergration , Data Selectin

Multiple Choice Multiple Answer


Question: Methods for outlier detection are categorised into following approaches :-
Correct Answer: Statistical , Distance based , Deviation based
Your Answer: Statistical , Distance based , Deviation based

Multiple Choice Single Answer


Question: Following clustering method is classified as being agglomerative or divisive :-
Correct Answer: Grid based
Your Answer: Grid based

Select The Blank


Question: In data warehouse architecture, the ________ component interleaves with and
connects other components.
Correct Answer: Metadata
Your Answer: Metadata

Multiple Choice Multiple Answer


Question: The ways of Intra query parallelization are :-
Correct Answer: Horizontal parallelization , Vertical Parallelization , Hybrid parallelization
Your Answer: Horizontal parallelization , Vertical Parallelization , Hybrid parallelization

Multiple Choice Multiple Answer


Question: The objective for physical design of data warehouse are :-
Correct Answer: Improve performance , Ensure scalability , Manage store
Your Answer: Improve performance , Ensure scalability , Manage database

True/False
Question: Metadata is building block of data warehouse.
Correct Answer: True
Your Answer: True

Page 37 of 89
SCDL – 4th Semester – Data Mining

Multiple Choice Single Answer


Question: What improves accuracy and speed of subsequent mining process?
Correct Answer: Integration
Your Answer: Regression

Select The Blank


Question: ________ are responsible for running queries and reports against data warehouse
tables.
Correct Answer: End users
Your Answer: End users

Select The Blank


Question: For operational system, the stored data contains ________values.
Correct Answer: Current data
Your Answer: Current data

Multiple Choice Single Answer


Question: Enterprise miner technique provides data mining algorithms including distinguishing
feature as :-
Correct Answer: Advanced Statistical and advanced visualization tool
Your Answer: Robust Graphics tools

Multiple Choice Multiple Answer


Question: Splitting of query by DBMS in intra query parallelization is for :-
Correct Answer: Index read , Data read , Data joint
Your Answer: Index read , Data read , Data joint

Multiple Choice Single Answer


Question: Which of the following approach requires more computation?
Correct Answer: Filter approach
Your Answer: Filter approach

True/False
Question: Data in warehouse is primarily for query.
Correct Answer: True
Your Answer: False

Multiple Choice Single Answer


Question: Simple matching approach is used for computing disimilarity between two objects for :-
Correct Answer: Nominal variable
Your Answer: Invariant variable

Select The Blank


Question: ________ are the inter platform devices that unable massive quantities of data to be
transported from one platform to another.
Correct Answer: Data ports
Your Answer: Data ports

Multiple Choice Multiple Answer


Question: Following are the types of normalization :-
Correct Answer: Min-Max Normalization , Z-score normalization , Normalization by scaling
Your Answer: Min-Max Normalization , Z-score normalization , Normalization by scaling

Multiple Choice Multiple Answer


Question: The different definitions of metadata are :-

Page 38 of 89
SCDL – 4th Semester – Data Mining

Correct Answer: Data about data , Catalog of data , Data warehouse roadmap
Your Answer: Data about data , Catalog of data , Data warehouse roadmap

Select The Blank


Question: ________ technique can be used to reduce the number of values for a given
continuous attribute by dividing range of attributes into interval.
Correct Answer: Descretization
Your Answer: Descretization

True/False
Question: MDDBMS stands for - Multilevel Database Management System.
Correct Answer: False
Your Answer: False

Multiple Choice Single Answer


Question: Main advantage of following which method is it's fast processing?
Correct Answer: Grid based
Your Answer: Grid based

Select The Blank


Question: ________ can store aggregate and detail data at varying levels of resolution or
abstraction.
Correct Answer: Index tree
Your Answer: Index tree

Select The Blank


Question: ________ architecture is more concerned with data access than memory access.
Correct Answer: MPP
Your Answer: SMP

LIST OF ATTEMPTED QUESTIONS AND ANSWERS

True/False
Question: Metadata is building block of data warehouse.
Correct Answer: True
Your Answer: True

Multiple Choice Multiple Answer


Question: The Main areas of Data Warehouse are :-
Correct Answer: Data acquisition , Data Storage , Information Delivery
Your Answer: Data Storage , Information Delivery , Data acquisition

Select The Blank


Question: ________ is the navigational map of data warehouse.
Correct Answer: End user Metadata
Your Answer: End user Metadata

Multiple Choice Multiple Answer


Question: Data mining Functionalities are :-
Correct Answer: Charactrization and Discrimination , Association Analysis , Cluster Analysis
Your Answer: Charactrization and Discrimination , Association Analysis , Cluster Analysis

Multiple Choice Single Answer


Question: Which of the following option is to share data by placing data at common place :-
Correct Answer: Shared disk

Page 39 of 89
SCDL – 4th Semester – Data Mining

Your Answer: Shared disk

Multiple Choice Multiple Answer


Question: Data mining is applicable to :-
Correct Answer: Relational Database , Data Warehouse , Transaction Database
Your Answer: Relational Database , Data Warehouse , Transaction Database

Multiple Choice Single Answer


Question: Which of the following approach requires more computation?
Correct Answer: Filter approach
Your Answer: Filter approach

Match The Following


Question Correct Answer Your Answer
Clustering Data tuples as objects Data tuples as objects
Dimension reduction Removal of irrelevant data Removal of irrelevant data
Data compression More computations More computations
Wrapper approach Great accuracy Great accuracy

Select The Blank


Question: According to ________ theory database schema consist of data and patterns that are
stored in database.
Correct Answer: Inductive databases
Your Answer: Inductive databases

True/False
Question: Data cubes created for varying levels of abstraction are referred as cuboids.
Correct Answer: True
Your Answer: True

Multiple Choice Multiple Answer


Question: The Architecture defines :-
Correct Answer: Measurements , Standard , General Design
Your Answer: Measurements , Standard , General Design

Multiple Choice Multiple Answer


Question: Source Data Component may be grouped into following categories :-
Correct Answer: Production Data , Internal External Data
Your Answer: Production Data , Internal External Data

Multiple Choice Multiple Answer


Question: When you use tool for design and development, following things take place with
metadata :-
Correct Answer: Metadata is no longer passive document , Metadata takes part in process ,
Metadata aids in automation of data warehouse process
Your Answer: Metadata aids in automation of data warehouse process , Metadata is no longer
passive document , Metadata takes part in process

True/False
Question: Metadata describes all the pertinent aspects of the data in data warehouse.
Correct Answer: True
Your Answer: True

Multiple Choice Multiple Answer


Question: Before moving data to data warehouse is has to go through :-
Correct Answer: Transformation , Integration , Consolidation

Page 40 of 89
SCDL – 4th Semester – Data Mining

Your Answer: Transformation , Integration , Consolidation

Match The Following


Question Correct Answer Your Answer
Disparate data Production data Production data
Non volatile data Query and analysis Query and analysis
Data granularity Level of detail Level of detail
Data from external External data External data
source

Select The Blank


Question: ________ is the time consuming and less feasible approach for filling missing values.
Correct Answer: Filling missing values manually
Your Answer: Use of row mean

Select The Blank


Question: ________ is an alternative aggolomerative hierarchical clustering algorithm.
Correct Answer: ROCK
Your Answer: ROCK

Multiple Choice Single Answer


Question: Which of the following is based on set of density distribution function clustering?
Correct Answer: DBSCAN
Your Answer: DBSCAN

True/False
Question: All data extraction, transformation, integration and staging jobs run on selected
hardware under chosen operating system.
Correct Answer: True
Your Answer: True

Select The Blank


Question: ________ component of warehouse is responsible for coordinating services and
activities within the data warehouse.
Correct Answer: Management and Control
Your Answer: Management and Control

Select The Blank


Question: ________ technique can be used to reduce the number of values for a given
continuous attribute by dividing range of attributes into interval.
Correct Answer: Descretization
Your Answer: Descretization

Multiple Choice Single Answer


Question: Which technique analyze experimental data?
Correct Answer: Analysis of variance
Your Answer: Analysis of variance

Multiple Choice Single Answer


Question: Classification rules are extracted from
Correct Answer: Decision Tree
Your Answer: Decision Tree

Select The Blank


Question: ________components consists all the different ways of making the information from
the data warehouse available to the user.

Page 41 of 89
SCDL – 4th Semester – Data Mining

Correct Answer: Information Delivery


Your Answer: Information Delivery

True/False
Question: In Linear regression data are modeled to fit a straight line.
Correct Answer: True
Your Answer: True

Select The Blank


Question: ________ platform is the platform on which the data warehouse DBMS runs and
database exist.
Correct Answer: Data storage
Your Answer: Data storage

Multiple Choice Single Answer


Question: In data reduction, the cluster representations of data are used to :-
Correct Answer: Replace data
Your Answer: Replace data

Multiple Choice Single Answer


Question: The DWT ( Discret Wavlet Transform) is a :-
Correct Answer: Linear single processing technique
Your Answer: Linear single processing technique

Multiple Choice Multiple Answer


Question: Substantial portion of Business metadata originates from :-
Correct Answer: Textual documents , Spreadsheets , Business rules
Your Answer: Textual documents , Spreadsheets , Business rules

True/False
Question: A distinct feature of DB Miner is its data cube based online analytical mining.
Correct Answer: True
Your Answer: True

Multiple Choice Multiple Answer


Question: Financial data called for banking and financial industry are often relatively :-
Correct Answer: Complete , Reliable , High Quality
Your Answer: Complete , Reliable , High Quality

True/False
Question: Smoothing by bin means each value in bin is replaced by the mean value of the
bucket.
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: SMP stands for :-
Correct Answer: Symmetric Multiprocessing
Your Answer: Symmetric Multiprocessing

Select The Blank


Question: In ________ type smoothing, minimum and maximum values in given bin are
identified as bin boundaries.
Correct Answer: Smoothing by bin boundaries
Your Answer: Smoothing by bin boundaries

Page 42 of 89
SCDL – 4th Semester – Data Mining

Select The Blank


Question: ________ is the method used to predict the value of response variable from one to
more variables.
Correct Answer: Regression
Your Answer: Regression

Multiple Choice Multiple Answer


Question: Data reduction reduces data size by :-
Correct Answer: Aggregation , Eliminating redundant features
Your Answer: Aggregation , Eliminating redundant features

True/False
Question: Sequential pattern analysis and similarity search techniques have been developed in
data mining.
Correct Answer: True
Your Answer: True

True/False
Question: Lower the level of detail, finer the data granularity.
Correct Answer: True
Your Answer: True

Select The Blank


Question: ________ is the user who has all access privileges like system, database
administrator, for table and views.
Correct Answer: Security administrator
Your Answer: Power user

Multiple Choice Multiple Answer


Question: Generalized linear model includes :-
Correct Answer: Logistic regression , Poisson regression
Your Answer: Logistic regression , Poisson regression

Multiple Choice Multiple Answer


Question: The main categories of Metadata in warehouse are :-
Correct Answer: Operational , Extraction and transformation Metadata , End user Metadata
Your Answer: Operational , Extraction and transformation Metadata , End user Metadata

Multiple Choice Single Answer


Question: Data migration affects performance requiring multiple blocks to be read which can be
adjusted by :-
Correct Answer: Block percent free
Your Answer: Block percent free

True/False
Question: Data Integration means multiple resourses may be combined.
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: Data reduction by volume can be used for data representation using which type of
reduction?
Correct Answer: Numerosity reduction
Your Answer: Numerosity reduction

Multiple Choice Single Answer

Page 43 of 89
SCDL – 4th Semester – Data Mining

Question: Effect of one attibute value on a given class is independent of values of other attibute
is called
Correct Answer: Value independence
Your Answer: Attirbute conditional independence

Multiple Choice Single Answer


Question: Which of the following technique involves placing and managing related units of data
in same physical block of storage
Correct Answer: Clustering
Your Answer: Clustering

LIST OF ATTEMPTED QUESTIONS AND ANSWERS

Multiple Choice Multiple Answer


Question: Data mining is applicable to :-
Correct Answer: Transaction Database , Relational Database , Data Warehouse
Your Answer: Transaction Database , Relational Database , Data Warehouse

Select The Blank


Question: ________ does not handle categorical attributes.
Correct Answer: CURE
Your Answer: Chameleon

Multiple Choice Single Answer


Question: Main advantage of following which method is it's fast processing?
Correct Answer: Grid based
Your Answer: Density based

Select The Blank


Question: When data block contains excessive amount of free space, performance ________
Correct Answer: Degenerates
Your Answer: Degenerates

Select The Blank


Question: ________components consists all the different ways of making the information from
the data warehouse available to the user.
Correct Answer: Information Delivery
Your Answer: Information Delivery

Multiple Choice Single Answer


Question: SMP stands for :-
Correct Answer: Symmetric Multiprocessing
Your Answer: Symmetric Multiprocessing

Multiple Choice Multiple Answer


Question: The need for metadata is for :-
Correct Answer: Using data warehouse , Building data warehouse , Administration of
warehouse
Your Answer: Building data warehouse , Administration of warehouse , Accessing data in
warehouse

Select The Blank

Page 44 of 89
SCDL – 4th Semester – Data Mining

Question: ________ are responsible for running queries and reports against data warehouse
tables.
Correct Answer: End users
Your Answer: Query tool specialist

Multiple Choice Multiple Answer


Question: Distinguishing characteristics of data warehouse architecture are :-
Correct Answer: Different Objective Scope , Data Content , Flexible and Dynamic
Your Answer: Data Content , Complete Analysis and Quick Response , Flexible and Dynamic

Multiple Choice Single Answer


Question: Redundancies can be deleted by :-
Correct Answer: Co-relational analysis
Your Answer: Relational analysis

True/False
Question: Moving data into staging area and performing data transformation function is a part of
data acquisition.
Correct Answer: True
Your Answer: True

Match The Following


Question Correct Answer Your Answer
Load Image To correspond to target files Offline data warehouse
Constructive merge New record supercedes Populating data warehouse table first
time
Initial Load Populating data warehouse Applying data
table first time
Incremental Load Applying ongoing changes Applying ongoing changes

True/False
Question: COBWEB incrementally incarporates objects into classification tree.
Correct Answer: True
Your Answer: True

Multiple Choice Multiple Answer


Question: Building blocks of Data Warehouse are :-
Correct Answer: Source Data , Data Staging , Management and Control
Your Answer: Source Data , Data Staging , Management and Control

True/False
Question: A process of grouping a set of physical or abstract objects into classes of similar
objects is called clusiering
Correct Answer: True
Your Answer: True

Multiple Choice Multiple Answer


Question: Application server serves following purposes :-
Correct Answer: To run middleware and establish connectivity , To execute management and
control software , To manage metadata
Your Answer: To run middleware and establish connectivity , To execute management and
control software , To run OLTP application

True/False
Question: Data mining often requires data integration.
Correct Answer: True

Page 45 of 89
SCDL – 4th Semester – Data Mining

Your Answer: True

Multiple Choice Single Answer


Question: The option "capture in source application technique of data extraction degrades
performance of source application because :-
Correct Answer: Additional processing needs
Your Answer: Additional processing needs

Multiple Choice Multiple Answer


Question: The main categories of Metadata in warehouse are :-
Correct Answer: Operational , Extraction and transformation Metadata , End user Metadata
Your Answer: Operational , Execution and Transformation Metadata , End user Metadata

Multiple Choice Single Answer


Question: Which of the following method creates copies of data in distributed environment?
Correct Answer: Replication
Your Answer: Replication

Multiple Choice Multiple Answer


Question: Common areas of application for mixed effect model includes :-
Correct Answer: Multiple data , Repeated measures data , Block designs
Your Answer: Multiple data , Repeated measures data , Block designs

Multiple Choice Multiple Answer


Question: Following are the issues to consider during data integration :-
Correct Answer: Detection and resolution of data values , Schema integration , Redundancy
Your Answer: Schema integration , Redundancy , Inconsistency

True/False
Question: Smoothing by bin means each value in bin is replaced by the mean value of the
bucket.
Correct Answer: True
Your Answer: True

Select The Blank


Question: In ________ duplicate sub trees exist within the tree.
Correct Answer: Repetition
Your Answer: Replication

Multiple Choice Multiple Answer


Question: The different analysis tools which are useful to detect unusual patterns such as large
amount of cash flow at certain period by certain group of people are :-
Correct Answer: Linkage analysis tool , Outlier analysis tool , Sequential pattern analysis tool
Your Answer: Linkage analysis tool , Complexity definition tool , Sequential pattern analysis tool

Select The Blank


Question: According to ________ theory database schema consist of data and patterns that are
stored in database.
Correct Answer: Inductive databases
Your Answer: Data compression

Multiple Choice Single Answer


Question: Which of the following methods for regression is used on sparse data :-
Correct Answer: Regression and log-linear model
Your Answer: Regression and log-linear model

Page 46 of 89
SCDL – 4th Semester – Data Mining

Multiple Choice Single Answer


Question: The big difference between data warehouse and any operational system is its :-
Correct Answer: Usage
Your Answer: Structure

Multiple Choice Single Answer


Question: In intermediate data extraction data capture through transaction log uses transaction
from :-
Correct Answer: Recovery from failure
Your Answer: Logs of successful transaction

Multiple Choice Multiple Answer


Question: SMP provides the features like :-
Correct Answer: Controllers which are accessible to all processors , Each processor has full
access to the shared memory though common bus , Each node has access to common set of
disks
Your Answer: Controllers which are accessible to all processors , Each node has access to
common set of disks , It is cluster of nodes

Match The Following


Question Correct Answer Your Answer
Data producer Responsible for data quality Foreign key preserved
Domain values Prevalent problem Primary key introduced
Update security Prevention of unauthorized Prevention of unauthorized
updates updates
Referential integrity Foreign key preserved Responsible for data quality

True/False
Question: Management architectural component manages and controls data acquisition
functions.
Correct Answer: True
Your Answer: False

Multiple Choice Single Answer


Question: EIS stands for :-
Correct Answer: Executive Information System
Your Answer: Extracted Integrated System

True/False
Question: NUMA provides better scalability than SMP.
Correct Answer: True
Your Answer: True

Select The Blank


Question: ________ architecture is more concerned with data access than memory access.
Correct Answer: MPP
Your Answer: MPP

Select The Blank


Question: Human being have around ________ gene.
Correct Answer: 100000
Your Answer: 1000000

Select The Blank


Question: With the widespread option of ________ real-time connection is viable for data
warehouse.

Page 47 of 89
SCDL – 4th Semester – Data Mining

Correct Answer: TCP/IP


Your Answer: TCP/IP

True/False
Question: In Linear regression data are modeled to fit a straight line.
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: Development and deployment of your data warehouse is joint effort between :-
Correct Answer: IT staff and user representatives
Your Answer: IT staff and developer

True/False
Question: Lower the level of detail, finer the data granularity.
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: Which of the following technique involves placing and managing related units of data
in same physical block of storage
Correct Answer: Clustering
Your Answer: Indexing

True/False
Question: Loan payment prediction and customer credit analysis are critical to business of bank.
Correct Answer: True
Your Answer: True

Select The Blank


Question: ________ is the platform for complex data transformation for the purpose of cleanse it
Correct Answer: Separate optimal Platform
Your Answer: Legacy platform

Select The Blank


Question: ________ clustering method follows statistical and neural network approach.
Correct Answer: Model based
Your Answer: Hierarchical Method

Multiple Choice Multiple Answer


Question: DNA sequences are comprised of :-
Correct Answer: Adenine , Gaunine , Thymine
Your Answer: Cytocine , Gaunine , Thymine

Multiple Choice Multiple Answer


Question: Business metadata is useful for :-
Correct Answer: Providing support to end users , For external view of data , Provides technical
support to search data
Your Answer: Providing support to end users , For external view of data , Provides technical
support to search data , Helps in searching data

Multiple Choice Single Answer


Question: Following clustering method is classified as being agglomerative or divisive :-
Correct Answer: Grid based
Your Answer: Grid based

Page 48 of 89
SCDL – 4th Semester – Data Mining

LIST OF ATTEMPTED QUESTIONS AND ANSWERS

Multiple Choice Multiple Answer


Question: Metadata in a data warehouse falls into following categories :-
Correct Answer: End-user Metadata , Operational Metadata , Extraction and Transformation
metadata
Your Answer: End-user Metadata , Operational Metadata , Extraction and Transformation
metadata

Multiple Choice Multiple Answer


Question: Classification and Prediction have following applications :-
Correct Answer: Credit approval , Medical Diagnosis , Performance Prediction
Your Answer: Credit approval , Performance Prediction , Selective Marketing

Multiple Choice Single Answer


Question: Data matrix is :-
Correct Answer: Object by variable structure
Your Answer: Two mode matrix

Match The Following


Question Correct Answer Your Answer
Disparate data Production data Internal data
Non volatile data Query and analysis Production data
Data granularity Level of detail Archive data
Data from external source External data Query and analysis

Multiple Choice Single Answer


Question: Bitmapped indexes are more suitable for data warehouse environment than for an
OLTP system
Correct Answer: Bitmapped index
Your Answer: B-Tree index

Multiple Choice Multiple Answer


Question: Building blocks of Data Warehouse are :-
Correct Answer: Source Data , Data Staging , Management and Control
Your Answer: Source Data , Data Staging , Management and Control

Multiple Choice Single Answer


Question: Queries run faster to find exact match using which type of indexing?
Correct Answer: Clustered index
Your Answer: Clustered index

True/False
Question: In Purning method, postpruning requires more computation than prepruning yet
generally leads to more reliable.
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: Which of the following option is to share data by placing data at common place :-
Correct Answer: Shared disk
Your Answer: Mass data transmission

Multiple Choice Single Answer

Page 49 of 89
SCDL – 4th Semester – Data Mining

Question: The category in which the value of each attribute is preserved as status every time a
change occurs is :-
Correct Answer: Periodic status
Your Answer: Periodic status

True/False
Question: In decision tree internal nodes are denoted by ovals and leaf nodes are denoted by
rectangles
Correct Answer: False
Your Answer: False

True/False
Question: Intelligent miner is an IBM data mining product.
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: Which from the following are special programs that are stored on database and fired
when certain predefined action occurs?
Correct Answer: Triggers
Your Answer: Triggers

Multiple Choice Single Answer


Question: Attribute construction is the part of :-
Correct Answer: Transformation
Your Answer: Transformation

True/False
Question: Metadata acts like a nerve center.
Correct Answer: True
Your Answer: True

Multiple Choice Multiple Answer


Question: Data reduction includes :-
Correct Answer: Single value decomposition , Wavelets , Regression
Your Answer: Wavelets , Regression

True/False
Question: Data cleansing means removing noisy and inconsistent data.
Correct Answer: True
Your Answer: True

True/False
Question: Data in warehouse is primarily for query.
Correct Answer: True
Your Answer: True

Multiple Choice Multiple Answer


Question: Preprocessing steps of data in order to help improve accuracy, efficiency and
scalability of classification & prediction are :-
Correct Answer: Data Cleaning , Relevance Analysis , Data Transformation
Your Answer: Data Cleaning , Data Transformation

Multiple Choice Multiple Answer


Question: Financial data called for banking and financial industry are often relatively :-
Correct Answer: Complete , Reliable , High Quality

Page 50 of 89
SCDL – 4th Semester – Data Mining

Your Answer: Complete , Reliable , Correct

Multiple Choice Single Answer


Question: Which of the option is not considered as the major function needed to get data ready?
Correct Answer: Storing data
Your Answer: Extracting data

Select The Blank


Question: ________ technique can be used to reduce the number of values for a given
continuous attribute by dividing range of attributes into interval.
Correct Answer: Descretization
Your Answer: Reduction

Multiple Choice Single Answer


Question: Simple matching approach is used for computing disimilarity between two objects for :-
Correct Answer: Nominal variable
Your Answer: Invariant variable

Multiple Choice Multiple Answer


Question: The ways of Intra query parallelization are :-
Correct Answer: Horizontal parallelization , Vertical Parallelization , Hybrid parallelization
Your Answer: Horizontal parallelization , Hybrid parallelization , Homogenous parallelization

True/False
Question: Legacy data resides on Hierarchical or Network database.
Correct Answer: True
Your Answer: True

Select The Blank


Question: Data cleansing and ________ methods of data mining helps in integration of genetic
data and construction of warehouse for genetic data analysis.
Correct Answer: Integration
Your Answer: Integration

Select The Blank


Question: ________ dimension of database in which primitive level data are spatial but
generalization becomes non spatial.
Correct Answer: Spatial to non spatial
Your Answer: Spatial to non spatial

Select The Blank


Question: ________ can store aggregate and detail data at varying levels of resolution or
abstraction.
Correct Answer: Index tree
Your Answer: Index tree

Multiple Choice Multiple Answer


Question: Following factors play important role in financial analysis :-
Correct Answer: Data warehouse , Data cubes , Outliner analysis
Your Answer: Data warehouse , Data cubes , Outliner analysis

Multiple Choice Multiple Answer


Question: Following are the types of normalization :-
Correct Answer: Min-Max Normalization , Z-score normalization , Normalization by scaling
Your Answer: Min-Max Normalization , Normalization by scaling

Page 51 of 89
SCDL – 4th Semester – Data Mining

Select The Blank


Question: ________ are responsible for running queries and reports against data warehouse
tables.
Correct Answer: End users
Your Answer: End users

Multiple Choice Single Answer


Question: Which of the following approach requires more computation?
Correct Answer: Filter approach
Your Answer: Wrapper approach

Select The Blank


Question: When data block contains excessive amount of free space, performance ________
Correct Answer: Degenerates
Your Answer: Degenerates

Multiple Choice Single Answer


Question: Which of the following type of processing provides high concurrency?
Correct Answer: SMP
Your Answer: MPP

Select The Blank


Question: ________ option of warehouse architecture provides incremental growth.
Correct Answer: Cluster
Your Answer: Cluster

Match The Following


Question Correct Answer Your Answer
Constructive merge New record supercedes New record supercedes
Initial Load Populating data warehouse Populating data warehouse
table first time table first time
Incremental Load Applying ongoing changes Applying ongoing changes
Load Image To correspond to target files To correspond to target files

Multiple Choice Multiple Answer


Question: Data cleansing routines work to clean the data by :-
Correct Answer: Filling missing values , Smoothing noisy data
Your Answer: Filling missing values , Smoothing noisy data , Resolving inconsistency

True/False
Question: From a Dataware house perspective data mining canbe viewed as an advanced stage
of Online Analytical Programming.
Correct Answer: True
Your Answer: True

Select The Blank


Question: ________ platform is the platform on which the data warehouse DBMS runs and
database exist.
Correct Answer: Data storage
Your Answer: Data storage

Multiple Choice Multiple Answer


Question: The smoothing techniques are :-
Correct Answer: Binning , Clustering , Regression
Your Answer: Clustering , Regression , Insertion

Page 52 of 89
SCDL – 4th Semester – Data Mining

True/False
Question: The elements of warehouse infrastructure are classified into operational and physical
infrastructure.
Correct Answer: True
Your Answer: True

Select The Blank


Question: It is good practice to drop ________ before initial load.
Correct Answer: Index
Your Answer: Splitting

Select The Blank


Question: ________ is an alternative aggolomerative hierarchical clustering algorithm.
Correct Answer: ROCK
Your Answer: CURE

Select The Blank


Question: Most of DBMS have ________ index techniques as default index techniques.
Correct Answer: B-Tree
Your Answer: B-Tree

True/False
Question: A distinguishing feature of Clementine is its object oriented extended module
interface.
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: Effect of one attibute value on a given class is independent of values of other attibute
is called
Correct Answer: Value independence
Your Answer: Value independence

Multiple Choice Multiple Answer


Question: The information delivery methods from data warehouse are :-
Correct Answer: Complex queries , MD Analysis , Statistical Analysis

LIST OF ATTEMPTED QUESTIONS AND ANSWERS

Multiple Choice Single Answer


Question: Capture at data source and that's why this method is quite reliable :-
Correct Answer: Capture by database Triggers
Your Answer: Capture in source application

Multiple Choice Single Answer


Question: Association rules mining is based on :-
Correct Answer: Clustering and Employing rules for classification
Your Answer: Rules for classification

Select The Blank


Question: A web server usually registers ________ entry for every access of a web page
Correct Answer: Weblog
Your Answer: Weblog

Page 53 of 89
SCDL – 4th Semester – Data Mining

Select The Blank


Question: In data warehouse architecture, the ________ component interleaves with and
connects other components.
Correct Answer: Metadata
Your Answer: Metadata

True/False
Question: To remove noise from data is called as Smoothing.
Correct Answer: True
Your Answer: True

Select The Blank


Question: Semantic integration of ________ genome database is the important task of DNA
analysis.
Correct Answer: Heterogeneous and distributed
Your Answer: Homogenous and stagnant

True/False
Question: Moving data into staging area and performing data transformation function is a part of
data acquisition.
Correct Answer: True
Your Answer: True

Select The Blank


Question: ________ does not handle categorical attributes.
Correct Answer: CURE
Your Answer: CURE

True/False
Question: Tools perform major functions in data warehouse environment.
Correct Answer: True
Your Answer: True

Multiple Choice Multiple Answer


Question: Common areas of application for mixed effect model includes :-
Correct Answer: Multiple data , Repeated measures data , Block designs
Your Answer: Multiple data , Dimensional data , Block designs

Multiple Choice Single Answer


Question: Bitmap index takes significantly less space than which type of index?
Correct Answer: B-Tree index
Your Answer: Clustered index

Multiple Choice Multiple Answer


Question: Data processing is done for :-
Correct Answer: Improving the efficiency , Ease of mining
Your Answer: Improving the efficiency , Removing redundancy , Removing complexity

Select The Blank


Question: ________ function of data staging component involves many forms of combining
pieces of data from different sources.
Correct Answer: Data Transformation
Your Answer: Data Transformation

Multiple Choice Multiple Answer


Question: Mining values can be removed by :-

Page 54 of 89
SCDL – 4th Semester – Data Mining

Correct Answer: Filling values manually , Use of global constant , Use of attribute mean
Your Answer: Filling values manually , Use of global constant , Use of row mean

Multiple Choice Multiple Answer


Question: The dimensions of spatial data cube are :-
Correct Answer: Non- spatial dimension , Spatial to non spatial , Spatial to spatial
Your Answer: Non- spatial dimension , Spatial to non spatial , Spatial to spatial

Select The Blank


Question: In ________ duplicate sub trees exist within the tree.
Correct Answer: Repetition
Your Answer: Replication

Select The Blank


Question: ________ are the inter platform devices that unable massive quantities of data to be
transported from one platform to another.
Correct Answer: Data ports
Your Answer: Data cubes

Match The Following


Question Correct Answer Your Answer
Data loading tool Primary key generation Formulating and running queries
Data modeling tool Reverse Engineering capabilities Primary key generation
Data Extraction tool Bulk extraction for full refresh Bulk extraction for full
refresh
Data transformation tool Default values Formulating and running queries

Select The Blank


Question: Most of the warehouses employ ________ database Management System.
Correct Answer: Relational
Your Answer: Relational

Multiple Choice Multiple Answer


Question: Metadata types can be classified as :-
Correct Answer: Business metadata , Technical metadata
Your Answer: Business metadata , Technical metadata , Logical metadata

True/False
Question: COBWEB is an extension of CLASSIT for incremental clustering of contineous data.
Correct Answer: False
Your Answer: True

Multiple Choice Single Answer


Question: Which type of analysis of DNA facilitates discovery of group of genes and study of
interaction and relationship between them?
Correct Answer: Association analysis
Your Answer: Generic data analysis

Multiple Choice Multiple Answer


Question: Following are the issues to consider during data integration :-
Correct Answer: Schema integration , Redundancy , Detection and resolution of data values
Your Answer: Schema integration , Redundancy , Detection and resolution of data values

Multiple Choice Single Answer


Question: Data migration affects performance requiring multiple blocks to be read which can be
adjusted by :-

Page 55 of 89
SCDL – 4th Semester – Data Mining

Correct Answer: Block percent free


Your Answer: Block percent vacant

Multiple Choice Multiple Answer


Question: Normalization improves :-
Correct Answer: Efficiency , Accuracy
Your Answer: Efficiency , Accuracy

True/False
Question: Smoothing by bin means each value in bin is replaced by the mean value of the
bucket.
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: In intermediate data extraction data capture through transaction log uses transaction
from :-
Correct Answer: Recovery from failure
Your Answer: All Transaction

Select The Blank


Question: Indexed ________ engines search index,web pages and build huge keyword based
indices which help to search sets of web pages containing certain keywords
Correct Answer: Web Search
Your Answer: Web Search

Multiple Choice Single Answer


Question: The first step of attibute oriented induction is :-
Correct Answer: Data focusing
Your Answer: Data Collection

Multiple Choice Single Answer


Question: Enterprise miner technique provides data mining algorithms including distinguishing
feature as :-
Correct Answer: Advanced Statistical and advanced visualization tool
Your Answer: Robust Graphics tools

Select The Blank


Question: ________ is density based clustering method which computes on augumented
clustering ordering for automic ordering for automatic and interactive cluster analysis
Correct Answer: DBSCAN
Your Answer: Hierachical

True/False
Question: A process of grouping a set of physical or abstract objects into classes of similar
objects is called clusiering
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: Grouped data can be analyzed with the technique :-
Correct Answer: Mixed effect model
Your Answer: Regression

Multiple Choice Multiple Answer


Question: Which of the following clustering analysis method uses multiresolution approach?

Page 56 of 89
SCDL – 4th Semester – Data Mining

Correct Answer: STING , Wave Cluster


Your Answer: STING , Only Wave Cluster

True/False
Question: COBWEB is a method of incremental conceptual clustering.
Correct Answer: True
Your Answer: True

Multiple Choice Multiple Answer


Question: Source Data Component may be grouped into following categories :-
Correct Answer: Production Data , Internal External Data
Your Answer: Production Data , Internal External Data , Non Analyzed data

Multiple Choice Single Answer


Question: Which type of indexing do not work with data whose selectivity is low :-
Correct Answer: B-Tree index
Your Answer: B-Tree index

True/False
Question: Easily accessible metadata is crucial for end users.
Correct Answer: True
Your Answer: False

Match The Following


Question Correct Answer Your Answer
Clementine Integral solutions SAS
Intelligent miner IBM IBM
Enterprise miner SAS DB miner technology
Mineset Silicon Graphics Integral solutions

Multiple Choice Single Answer


Question: Data can be smoothed by filling the data to function such as :-
Correct Answer: Regression
Your Answer: Clustering

True/False
Question: Data mining is not that much powerful tool for vast data such as gene sequences in
DNA analysis.
Correct Answer: True
Your Answer: True

Multiple Choice Multiple Answer


Question: The need for metadata is for :-
Correct Answer: Using data warehouse , Building data warehouse , Administration of
warehouse
Your Answer: Using data warehouse , Building data warehouse , Administration of warehouse

Multiple Choice Multiple Answer


Question: The Architecture defines :-
Correct Answer: Measurements , Standard , General Design
Your Answer: Measurements , General Design , Standard Techniques

Multiple Choice Multiple Answer


Question: Following are the theories for the basis of data mining :-
Correct Answer: Pattern discovery , Probability theory , Microeconomic view
Your Answer: Pattern discovery , Probability theory , Macroeconomic view

Page 57 of 89
SCDL – 4th Semester – Data Mining

Select The Blank


Question: In ________ type smoothing, minimum and maximum values in given bin are
identified as bin boundaries.
Correct Answer: Smoothing by bin boundaries
Your Answer: Smoothing by bin boundaries

True/False
Question: Data Integration means multiple resourses may be combined.
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: Which of the following function involves data cleaning, data standardizing and
summarizing?
Correct Answer: Transforming data
Your Answer: Transforming data

LIST OF ATTEMPTED QUESTIONS AND ANSWERS

Select The Blank


Question: For operational system, the stored data contains ________values.
Correct Answer: Current data
Your Answer: Current data

Select The Blank


Question: ________ is the user who has system access privileges but no database
administration privileges as well as not for table and views.
Correct Answer: Network administrator
Your Answer: Security administrator

Multiple Choice Single Answer


Question: Selection of which part of data warehouse hardware is ' Bit your bottom dollar'?
Correct Answer: Server hardware
Your Answer: Workstation hardware

Multiple Choice Single Answer


Question: The Clustering method DBSCAN stands for :-
Correct Answer: Desity Based Spatial clustering of Application with Noise
Your Answer: Desity Based Spatial clustering of Application with Noise

Multiple Choice Single Answer


Question: Which of the option is not considered as the major function needed to get data ready?
Correct Answer: Storing data
Your Answer: Storing data

Multiple Choice Single Answer


Question: Which from the following are special programs that are stored on database and fired
when certain predefined action occurs?
Correct Answer: Triggers
Your Answer: Triggers

Multiple Choice Multiple Answer


Question: User must have proper access to metadata for performing responsibilities of :-

Page 58 of 89
SCDL – 4th Semester – Data Mining

Correct Answer: Design , Administration


Your Answer: Administration , Management

True/False
Question: Architecture comes first, tools follows it.
Correct Answer: True
Your Answer: True

True/False
Question: In the data acquisition area, the data flow begins at the data sources and pauses at
staging area.
Correct Answer: True
Your Answer: False

Multiple Choice Single Answer


Question: OPTICS regarding clustering stands for :-
Correct Answer: Ordering Points to identify the clustering Structure
Your Answer: Ordering Points to identify the clustering Structure

Multiple Choice Multiple Answer


Question: In data storage area metadata recorded by processes is used for :-
Correct Answer: Users , Development , Administration
Your Answer: Development , Administration

Multiple Choice Multiple Answer


Question: Data reduction reduces data size by :-
Correct Answer: Aggregation , Eliminating redundant features
Your Answer: Aggregation , Eliminating redundant features

Multiple Choice Single Answer


Question: Which of the following is based on set of density distribution function clustering?
Correct Answer: DBSCAN
Your Answer: DBSCAN

True/False
Question: A distinct feature of DB Miner is its data cube based online analytical mining.
Correct Answer: True
Your Answer: True

True/False
Question: Metadata describes all the pertinent aspects of the data in data warehouse.
Correct Answer: True
Your Answer: True

Match The Following


Question Correct Answer Your Answer
Extraction is manual/Tool based Method of extraction Method of extraction
Identify source application Source identification Source identification
Denote time window Time window Time window
Handling unextractable input records Exception handling Exception handling

Multiple Choice Single Answer


Question: The stored values of an attribute represents the value of attribute at this moment of
time is :-
Correct Answer: Current value
Your Answer: Current attribute

Page 59 of 89
SCDL – 4th Semester – Data Mining

True/False
Question: The Structure that brings all the components together is known as Architecture.
Correct Answer: True
Your Answer: True

Select The Blank


Question: ________ is the navigational map of data warehouse.
Correct Answer: End user Metadata
Your Answer: End user Metadata

Multiple Choice Single Answer


Question: Simple matching approach is used for computing disimilarity between two objects for :-
Correct Answer: Nominal variable
Your Answer: Nominal variable

Multiple Choice Multiple Answer


Question: Preprocessing steps of data in order to help improve accuracy, efficiency and
scalability of classification & prediction are :-
Correct Answer: Data Cleaning , Relevance Analysis , Data Transformation
Your Answer: Data Cleaning , Relevance Analysis

Multiple Choice Single Answer


Question: Which of the following clustering algorithm integrates density based and grid based
clustering?
Correct Answer: CLQUE
Your Answer: STING

True/False
Question: Data mining is not that much powerful tool for vast data such as gene sequences in
DNA analysis.
Correct Answer: True
Your Answer: True

Select The Blank


Question: ________ is the time consuming and less feasible approach for filling missing values.
Correct Answer: Filling missing values manually
Your Answer: Filling missing values manually

Match The Following


Question Correct Answer Your Answer
Disparate data Production data Production data
Non volatile data Query and analysis Query and analysis
Data granularity Level of detail Level of detail
Data from external source External data External data

True/False
Question: Sequential pattern analysis and similarity search techniques have been developed in
data mining.
Correct Answer: True
Your Answer: True

Multiple Choice Multiple Answer


Question: Data processing is done for :-
Correct Answer: Improving the efficiency , Ease of mining
Your Answer: Improving the efficiency , Ease of mining

Page 60 of 89
SCDL – 4th Semester – Data Mining

Multiple Choice Multiple Answer


Question: The smoothing techniques are :-
Correct Answer: Binning , Clustering , Regression
Your Answer: Binning , Clustering , Regression

Multiple Choice Single Answer


Question: Many methods for data smoothing are also methods for data reduction involving :-
Correct Answer: Discretization
Your Answer: Discretization

Multiple Choice Single Answer


Question: In data reduction, the cluster representations of data are used to :-
Correct Answer: Replace data
Your Answer: Represent actual data

True/False
Question: In Purning method, postpruning requires more computation than prepruning yet
generally leads to more reliable.
Correct Answer: True
Your Answer: True

Select The Blank


Question: ________ component of warehouse is responsible for coordinating services and
activities within the data warehouse.
Correct Answer: Management and Control
Your Answer: Management and Control

Select The Blank


Question: ________ function of data staging component involves many forms of combining
pieces of data from different sources.
Correct Answer: Data Transformation
Your Answer: Data Transformation

Multiple Choice Single Answer


Question: Which type of following clustering computes augumented cluster ordering?
Correct Answer: OPTICS
Your Answer: CLQUE

True/False
Question: Data cleansing means removing noisy and inconsistent data.
Correct Answer: True
Your Answer: True

Multiple Choice Multiple Answer


Question: Classification and Prediction have following applications :-
Correct Answer: Credit approval , Medical Diagnosis , Performance Prediction
Your Answer: Credit approval , Medical Diagnosis , Performance Prediction

Select The Blank


Question: Creating ________is violation of Normalization principles.
Correct Answer: Array
Your Answer: Structure

Multiple Choice Multiple Answer


Question: The areas of classification for metadata are :-

Page 61 of 89
SCDL – 4th Semester – Data Mining

Correct Answer: Development/usage , Technical/business , BackRoom/Front Room


Your Answer: Development/usage , BackRoom/Front Room , Administration

Select The Blank


Question: ________ databases are one of the most poplularly available and rich information
repositories.
Correct Answer: Relational
Your Answer: Relational

Multiple Choice Multiple Answer


Question: The ways of Intra query parallelization are :-
Correct Answer: Horizontal parallelization , Vertical Parallelization , Hybrid parallelization
Your Answer: Horizontal parallelization , Vertical Parallelization , Hybrid parallelization

True/False
Question: Data Mining refers to extracting knowledge from larger amount of data.
Correct Answer: True
Your Answer: True

Multiple Choice Multiple Answer


Question: Data base miner provides multiple data mining algorithms including :-
Correct Answer: Discovery driven OLAP analysis , Association , Classification
Your Answer: Association , Classification , Regression

Multiple Choice Multiple Answer


Question: Data transformation includes :-
Correct Answer: Smoothing , Aggregation , Generalization
Your Answer: Smoothing , Aggregation , Generalization

Select The Blank


Question: ________ includes Normalization and Aggregation as data preprocessing procedures.
Correct Answer: Data transformation
Your Answer: Data transformation

Multiple Choice Single Answer


Question: Association rules mining is based on :-
Correct Answer: Clustering and Employing rules for classification
Your Answer: Clustering and Employing rules for classification

Select The Blank


Question: Semantic integration of ________ genome database is the important task of DNA
analysis.
Correct Answer: Heterogeneous and distributed
Your Answer: Heterogeneous and distributed

Select The Blank


Question: ________ regression involves finding the best time to fit two variables.
Correct Answer: Linear
Your Answer: Linear

LIST OF ATTEMPTED QUESTIONS AND ANSWERS

True/False
Question: Data cubes created for varying levels of abstraction are referred as cuboids.

Page 62 of 89
SCDL – 4th Semester – Data Mining

Correct Answer: True


Your Answer: True

True/False
Question: Data mining is not that much powerful tool for vast data such as gene sequences in
DNA analysis.
Correct Answer: True
Your Answer: True

Select The Blank


Question: ________ pilot proves validity of data warehousing concept to users and top
management.
Correct Answer: Proof of concept
Your Answer: User tool appreciation

Multiple Choice Multiple Answer


Question: Mining values can be removed by :-
Correct Answer: Filling values manually , Use of global constant , Use of attribute mean
Your Answer: Filling values manually , Use of global constant , Use of attribute mean

Multiple Choice Single Answer


Question: Which of the following type of processing provides high concurrency?
Correct Answer: SMP
Your Answer: SMP

True/False
Question: Lower the level of detail, finer the data granularity.
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: Effect of one attibute value on a given class is independent of values of other attibute
is called
Correct Answer: Value independence
Your Answer: Value independence

Select The Blank


Question: According to ________ theory database schema consist of data and patterns that are
stored in database.
Correct Answer: Inductive databases
Your Answer: Inductive databases

True/False
Question: A cluster is a collection of similar data objects in same cluster and disimilar to objects
in another cluster.
Correct Answer: True
Your Answer: True

Multiple Choice Multiple Answer


Question: Warehouse Operational infrastructure is to support each architecture component
consists of :-
Correct Answer: People , Procedures , Management software
Your Answer: People , Procedures , Management software

Multiple Choice Multiple Answer


Question: Time variant nature of the data in data warehouse :-

Page 63 of 89
SCDL – 4th Semester – Data Mining

Correct Answer: Allows for analysis of the past , Relate information to the present , Enables
forecasts for the future
Your Answer: Allows for analysis of the past , Relate information to the present , Enables
forecasts for the future

Multiple Choice Multiple Answer


Question: Methods for outlier detection are categorised into following approaches :-
Correct Answer: Statistical , Distance based , Deviation based
Your Answer: Distance based , Deviation based , Diversion based

Select The Blank


Question: ________ regression involves finding the best time to fit two variables.
Correct Answer: Linear
Your Answer: Linear

Multiple Choice Single Answer


Question: Association rules mining is based on :-
Correct Answer: Clustering and Employing rules for classification
Your Answer: Clustering and Employing rules for classification

True/False
Question: Smoothing by bin means each value in bin is replaced by the mean value of the
bucket.
Correct Answer: True
Your Answer: True

True/False
Question: Metadata describes all the pertinent aspects of the data in data warehouse.
Correct Answer: True
Your Answer: True

Multiple Choice Multiple Answer


Question: Following are the theories for the basis of data mining :-
Correct Answer: Pattern discovery , Probability theory , Microeconomic view
Your Answer: Microeconomic view , Pattern discovery , Probability theory

Multiple Choice Single Answer


Question: Which technique is used to predict categorical response variable?
Correct Answer: Discriminant analysis
Your Answer: Analysis of variance

Multiple Choice Single Answer


Question: EIS stands for :-
Correct Answer: Executive Information System
Your Answer: Executive Information System

Match The Following


Question Correct Answer Your Answer
Integration Data merging from multiple sources Data merging from multiple sources
Binning Sorted, neighbourhood data Sorted, neighbourhood data
Clustering Similar values Similar values
Regression Filtering of data Filtering of data

Multiple Choice Single Answer


Question: The DWT ( Discret Wavlet Transform) is a :-
Correct Answer: Linear single processing technique

Page 64 of 89
SCDL – 4th Semester – Data Mining

Your Answer: Linear single processing technique

True/False
Question: Data mining often requires data integration.
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: Which is the typical example of Grid based clustering method
Correct Answer: STING
Your Answer: DBSCAN

Multiple Choice Single Answer


Question: Classification rules are extracted from
Correct Answer: Decision Tree
Your Answer: Decision Tree

Multiple Choice Multiple Answer


Question: For processing metadata in informal delivery area, data can be referred back for :-
Correct Answer: Source data configuration , Data structure , Data transformation
Your Answer: Source data configuration , Data structure , Data transformation

Match The Following


Question Correct Answer Your Answer
Constructive merge New record supercedes New record supercedes
Initial Load Populating data warehouse Populating data warehouse table first
table first time time
Incremental Load Applying ongoing changes Applying ongoing changes
Load Image To correspond to target files To correspond to target files

Select The Blank


Question: ________ is the clustering method which encounters difficultes regarding the selection
of merge/split points
Correct Answer: Hierachical
Your Answer: Hierachical

Multiple Choice Multiple Answer


Question: Substantial portion of Business metadata originates from :-
Correct Answer: Textual documents , Spreadsheets , Business rules
Your Answer: Textual documents , Spreadsheets , Business rules

True/False
Question: In Purning method, postpruning requires more computation than prepruning yet
generally leads to more reliable.
Correct Answer: True
Your Answer: True

Select The Blank


Question: Human being have around ________ gene.
Correct Answer: 100000
Your Answer: 100000

Multiple Choice Single Answer


Question: Which of the following type executes query operations in pipeline manner?
Correct Answer: Vertical parallelism
Your Answer: Vertical parallelism

Page 65 of 89
SCDL – 4th Semester – Data Mining

Select The Blank


Question: In ________ duplicate sub trees exist within the tree.
Correct Answer: Repetition
Your Answer: Repetition

Multiple Choice Single Answer


Question: Real world databases are highly susceptible to noisy, missing and inconsistent data
due to :-
Correct Answer: Huge size of data
Your Answer: Complexity in data

Multiple Choice Single Answer


Question: The technique of data clustering facilitates :-
Correct Answer: Serial access
Your Answer: Random access

Multiple Choice Multiple Answer


Question: Before moving data to data warehouse is has to go through :-
Correct Answer: Transformation , Integration , Consolidation
Your Answer: Integration , Summarization , Consolidation

Multiple Choice Single Answer


Question: Bayes Theorem is :-
Correct Answer: P(H|X)=P(X|H)(P)/P(X)
Your Answer: P(H|X)=P(X)(PH)/P(X|H)

True/False
Question: MDDBMS stands for - Multilevel Database Management System.
Correct Answer: False
Your Answer: False

Multiple Choice Multiple Answer


Question: DNA sequences are comprised of :-
Correct Answer: Adenine , Gaunine , Thymine
Your Answer: Adenine , Cytocine , Gaunine , Thymine

Multiple Choice Multiple Answer


Question: Financial data called for banking and financial industry are often relatively :-
Correct Answer: Complete , Reliable , High Quality
Your Answer: Complete , Reliable , High Quality

Multiple Choice Single Answer


Question: Deviation based outlier detection identifes outliers by :-
Correct Answer: Examining character of objects in groups
Your Answer: Examining distance between objects

Multiple Choice Multiple Answer


Question: The functions of data acquisition are :-
Correct Answer: Data Extraction , Data Transformation
Your Answer: Data Extraction , Data Transformation , Data cleansing , Data storing

Select The Blank


Question: ________ databases are one of the most poplularly available and rich information
repositories.
Correct Answer: Relational

Page 66 of 89
SCDL – 4th Semester – Data Mining

Your Answer: Relational

Multiple Choice Single Answer


Question: A Wavelet transformation is :-
Correct Answer: Single processing Technique that decomposes signals into different frequency
subbands
Your Answer: Single processing Technique that composes signals into different frequency
subbands

Select The Blank


Question: Creating ________is violation of Normalization principles.
Correct Answer: Array
Your Answer: Array

Select The Blank


Question: ________ method of regression is useful when errors fails to satisfy normal
conditions.
Correct Answer: Robust
Your Answer: Robust

True/False
Question: Sequential pattern analysis and similarity search techniques have been developed in
data mining.
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: SMP stands for :-
Correct Answer: Symmetric Multiprocessing
Your Answer: Symmetric Multiprocessing

LIST OF ATTEMPTED QUESTIONS AND ANSWERS sheetu 2

Multiple Choice Multiple Answer


Question: Data Mining means :-
Correct Answer: Knowledge mining from database , Data /Pattern analysis , Data Archelogy
Your Answer: Data Archelogy , Knowledge mining from database , Data /Pattern analysis

Select The Blank


Question: ________ technique contribute to machine learning, neural network, association
mining, sequential pattern mining.
Correct Answer: Pattern discovery
Your Answer: Pattern discovery

Match The Following


Question Correct Answer Your Answer
Operating systems Security, reliability, availability Security, reliability, availability
Compatibility
Data Acquisition Data Extraction, Data Extraction, Transformation,
Transformation, cleansing, cleansing, integration
integration
Data Storage Data loading , Archiving Data loading , Archiving
Information Delivery Report generation, query Report generation, query processing
processing and complex and complex analysis
analysis

Page 67 of 89
SCDL – 4th Semester – Data Mining

True/False
Question: The Structure that brings all the components together is known as Architecture.
Correct Answer: True
Your Answer: True

Multiple Choice Multiple Answer


Question: Advantages of Wavelet transformation for clustering are :-
Correct Answer: Unsupervised clustering , Detection of cluster for accuracy , Clustering is fast
Your Answer: Unsupervised clustering , Detection of cluster for accuracy , Decomposition of
cluster for accuracy

Multiple Choice Multiple Answer


Question: The Main areas of Data Warehouse are :-
Correct Answer: Data acquisition , Data Storage , Information Delivery
Your Answer: Data Stage , Data Storage , Information Delivery

True/False
Question: In decision tree internal nodes are denoted by ovals and leaf nodes are denoted by
rectangles
Correct Answer: False
Your Answer: False

True/False
Question: In Database system multidimensional index trees are primarily used for providing fast
data access.
Correct Answer: True
Your Answer: True

Select The Blank


Question: ________ is the platform for complex data transformation for the purpose of cleanse it
Correct Answer: Separate optimal Platform
Your Answer: Separate optimal Platform

Multiple Choice Single Answer


Question: Bitmapped indexes are more suitable for data warehouse environment than for an
OLTP system
Correct Answer: Bitmapped index
Your Answer: Bitmapped index

Multiple Choice Single Answer


Question: The Clustering method DBSCAN stands for :-
Correct Answer: Desity Based Spatial clustering of Application with Noise
Your Answer: Desity Based Spatial clustering of Application with Noise

Select The Blank


Question: ________ is an alternative aggolomerative hierarchical clustering algorithm.
Correct Answer: ROCK
Your Answer: ROCK

Multiple Choice Single Answer


Question: Query tool is meant for :-
Correct Answer: Data acquisition
Your Answer: Information delivery

Select The Blank

Page 68 of 89
SCDL – 4th Semester – Data Mining

Question: ________ are responsible for running queries and reports against data warehouse
tables.
Correct Answer: End users
Your Answer: End users

Multiple Choice Multiple Answer


Question: Classification and Prediction have following applications :-
Correct Answer: Credit approval , Medical Diagnosis , Performance Prediction
Your Answer: Credit approval , Medical Diagnosis , Performance Prediction

Select The Blank


Question: ________ architecture is more concerned with data access than memory access.
Correct Answer: MPP
Your Answer: MPP

Select The Blank


Question: ________ are the inter platform devices that unable massive quantities of data to be
transported from one platform to another.
Correct Answer: Data ports
Your Answer: Data ports

Multiple Choice Single Answer


Question: Which technique analyze experimental data?
Correct Answer: Analysis of variance
Your Answer: Regression

True/False
Question: Data classification is two step process in which first step includes classfication of
model and in second step model describes set of data.
Correct Answer: False
Your Answer: True

Select The Blank


Question: ________ clustering method follows statistical and neural network approach.
Correct Answer: Model based
Your Answer: Model based

Multiple Choice Single Answer


Question: Which of the following methods for regression is used on sparse data :-
Correct Answer: Regression and log-linear model
Your Answer: Regression and log-linear model

True/False
Question: Audio data mining can be an interesting alternative to visual mining.
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: If many indexes are needed, then on which table which option is more preferable?
Correct Answer: Splitting of tables
Your Answer: Collecting of tables

Select The Blank


Question: Indexed ________ engines search index,web pages and build huge keyword based
indices which help to search sets of web pages containing certain keywords
Correct Answer: Web Search

Page 69 of 89
SCDL – 4th Semester – Data Mining

Your Answer: Web Search

Multiple Choice Multiple Answer


Question: Distinguishing characteristics of data warehouse architecture are :-
Correct Answer: Different Objective Scope , Data Content , Flexible and Dynamic
Your Answer: Different Objective Scope , Data Content , Flexible and Dynamic

Multiple Choice Single Answer


Question: Which type of analysis of DNA facilitates discovery of group of genes and study of
interaction and relationship between them?
Correct Answer: Association analysis
Your Answer: Association analysis

True/False
Question: Noise in data means error or variance in measured variable.
Correct Answer: True
Your Answer: True

Select The Blank


Question: ________ is the user who has all access privileges like system, database
administrator, for table and views.
Correct Answer: Security administrator
Your Answer: Security administrator

Multiple Choice Multiple Answer


Question: The main categories of Metadata in warehouse are :-
Correct Answer: Operational , Extraction and transformation Metadata , End user Metadata
Your Answer: Operational , Extraction and transformation Metadata , End user Metadata

Multiple Choice Single Answer


Question: Simple matching approach is used for computing disimilarity between two objects for :-
Correct Answer: Nominal variable
Your Answer: Nominal variable

True/False
Question: One of the most important search problem in genetic analysis is similarity search and
comparison among DNA sequence.
Correct Answer: True
Your Answer: True

True/False
Question: Data cube stores multidimensional aggregate information.
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: Large number of indexes affects the loading process because :-
Correct Answer: Indexes are created for new records
Your Answer: Searching record becomes difficult

Select The Blank


Question: Most of the warehouses employ ________ database Management System.
Correct Answer: Relational
Your Answer: Relational

Multiple Choice Single Answer

Page 70 of 89
SCDL – 4th Semester – Data Mining

Question: In intermediate data extraction data capture through transaction log uses transaction
from :-
Correct Answer: Recovery from failure
Your Answer: Recovery from failure

Multiple Choice Single Answer


Question: Redundancies can be deleted by :-
Correct Answer: Co-relational analysis
Your Answer: Co-relational analysis

True/False
Question: Descriptive mining takes perform ingerence on current data which predictive mining
characterize the general properties of data in database
Correct Answer: False
Your Answer: True

Select The Blank


Question: When data block contains excessive amount of free space, performance ________
Correct Answer: Degenerates
Your Answer: Degenerates

Multiple Choice Multiple Answer


Question: The smoothing techniques are :-
Correct Answer: Binning , Clustering , Regression
Your Answer: Binning , Clustering , Regression

True/False
Question: A process of grouping a set of physical or abstract objects into classes of similar
objects is called clusiering
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: For Banking and financial data which type of analysis is used?
Correct Answer: Multidimensional
Your Answer: Relational

Multiple Choice Multiple Answer


Question: The dimensions of spatial data cube are :-
Correct Answer: Non- spatial dimension , Spatial to non spatial , Spatial to spatial
Your Answer: Non- spatial dimension , Spatial to non spatial , Spatial to spatial

Multiple Choice Single Answer


Question: Which of the following technique involves placing and managing related units of data
in same physical block of storage
Correct Answer: Clustering
Your Answer: Clustering

Multiple Choice Multiple Answer


Question: Data processing techniques are :-
Correct Answer: Cleansing , Integration , Transformation
Your Answer: Cleansing , Integration , Transformation

Match The Following


Question Correct Answer Your Answer
Clustering Data tuples as objects Great accuracy

Page 71 of 89
SCDL – 4th Semester – Data Mining

Dimension reduction Removal of irrelevant data Removal of irrelevant data


Data compression More computations Encoding mechanism
Wrapper approach Great accuracy Data reduction

Select The Blank


Question: ________ can store aggregate and detail data at varying levels of resolution or
abstraction.
Correct Answer: Index tree
Your Answer: Index tree

Multiple Choice Multiple Answer


Question: Following are the issues to consider during data integration :-
Correct Answer: Schema integration , Redundancy , Detection and resolution of data values
Your Answer: Schema integration , Redundancy , Detection and resolution of data values

LIST OF ATTEMPTED QUESTIONS AND ANSWERS

Multiple Choice Single Answer


Question: Histograms, the methods to store reduced representation of data uses :-
Correct Answer: Binning
Your Answer: Aggregation

Multiple Choice Single Answer


Question: Which of the following is based on set of density distribution function clustering?
Correct Answer: DBSCAN
Your Answer: DBSCAN

Multiple Choice Multiple Answer


Question: Source Data Component may be grouped into following categories :-
Correct Answer: Production Data , Internal External Data
Your Answer: Production Data , Internal External Data

Select The Blank


Question: ________ does not handle categorical attributes.
Correct Answer: CURE
Your Answer: CURE

Select The Blank


Question: Semantic integration of ________ genome database is the important task of DNA
analysis.
Correct Answer: Heterogeneous and distributed
Your Answer: Heterogeneous and distributed

True/False
Question: Data staging and data storage may start out on same computing platform.
Correct Answer: True
Your Answer: True

True/False
Question: Data in data warehouse cuts across application.
Correct Answer: True
Your Answer: False

True/False
Question: Loan payment prediction and customer credit analysis are critical to business of bank.

Page 72 of 89
SCDL – 4th Semester – Data Mining

Correct Answer: True


Your Answer: True

Multiple Choice Multiple Answer


Question: Data integration means :-
Correct Answer: Integrating database , Integrating cubes , Integrating files
Your Answer: Integrating cubes , Integrating files , Integrating attributes

Multiple Choice Multiple Answer


Question: Data mining is applicable to :-
Correct Answer: Relational Database , Data Warehouse , Transaction Database
Your Answer: Relational Database , Data Warehouse , Transaction Database

Multiple Choice Multiple Answer


Question: The information delivery methods from data warehouse are :-
Correct Answer: Complex queries , MD Analysis , Statistical Analysis
Your Answer: Complex queries , MD Analysis , Statistical Analysis

Multiple Choice Multiple Answer


Question: SMP provides the features like :-
Correct Answer: Controllers which are accessible to all processors , Each processor has full
access to the shared memory though common bus , Each node has access to common set of
disks
Your Answer: Controllers which are accessible to all processors , Each processor has full
access to the shared memory though common bus , Each node has access to common set of
disks

Multiple Choice Multiple Answer


Question: Splitting of query by DBMS in intra query parallelization is for :-
Correct Answer: Index read , Data read , Data joint
Your Answer: Index read , Data read , Data joint

Multiple Choice Single Answer


Question: For Incremental data loads the sequence is :-
Correct Answer: Triggering ->Filtering ->data extraction -> Transformation ->Integration
->cleansing
Your Answer: Triggering ->data extraction ->Filtering -> Transformation ->Integration
->cleansing

Multiple Choice Multiple Answer


Question: The platform of Data warehouse consists of :-
Correct Answer: Basic hardware components , Operating System , Network and Network
software
Your Answer: Operating System , Network and Network software , Utility software

Multiple Choice Multiple Answer


Question: Following factors play important role in financial analysis :-
Correct Answer: Data warehouse , Data cubes , Outliner analysis
Your Answer: Data warehouse , Data cubes , Outliner analysis

Multiple Choice Single Answer


Question: Which of the following data capture method of data abstraction is time consuming?
Correct Answer: Capture by comparing files
Your Answer: Capture by comparing files

Multiple Choice Single Answer

Page 73 of 89
SCDL – 4th Semester – Data Mining

Question: Capture at data source and that's why this method is quite reliable :-
Correct Answer: Capture by database Triggers
Your Answer: Capture by database Triggers

True/False
Question: To remove noise from data is called as Smoothing.
Correct Answer: True
Your Answer: True

True/False
Question: NUMA provides better scalability than SMP.
Correct Answer: True
Your Answer: True

Multiple Choice Multiple Answer


Question: The Architecture defines :-
Correct Answer: Measurements , Standard , General Design
Your Answer: Measurements , Standard , General Design

Multiple Choice Multiple Answer


Question: Data reduction includes :-
Correct Answer: Single value decomposition , Wavelets , Regression
Your Answer: Single value decomposition , Wavelets , Regression

Multiple Choice Single Answer


Question: Which of the following component includes database Management System?
Correct Answer: Data Storage
Your Answer: Management and control

Match The Following


Question Correct Answer Your Answer
Data loading tool Primary key generation Primary key generation
Data modeling tool Reverse Engineering Reverse Engineering capabilities
capabilities
Data Extraction tool Bulk extraction for full Bulk extraction for full refresh
refresh
Data transformation Default values Default values
tool

Multiple Choice Single Answer


Question: Which type of following clustering computes augumented cluster ordering?
Correct Answer: OPTICS
Your Answer: OPTICS

Multiple Choice Single Answer


Question: Which from the following are special programs that are stored on database and fired
when certain predefined action occurs?
Correct Answer: Triggers
Your Answer: Triggers

Multiple Choice Single Answer


Question: Attribute construction is the part of :-
Correct Answer: Transformation
Your Answer: Transformation

Multiple Choice Single Answer

Page 74 of 89
SCDL – 4th Semester – Data Mining

Question: The stored values of an attribute represents the value of attribute at this moment of
time is :-
Correct Answer: Current value
Your Answer: Current value

Multiple Choice Single Answer


Question: The option "capture in source application technique of data extraction degrades
performance of source application because :-
Correct Answer: Additional processing needs
Your Answer: Additional processing needs

Select The Blank


Question: ________ technique is the statistical technique for analyzing data.
Correct Answer: Time series
Your Answer: Analysis of variance

Select The Blank


Question: ________ function of data staging component involves many forms of combining
pieces of data from different sources.
Correct Answer: Data Transformation
Your Answer: Data Transformation

True/False
Question: To detect money laundering and other financial crimes, it is important to integrate
information for multiple databases.
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: Which of the following option of data extraction is known as application assisted data
capture?
Correct Answer: Capture in source application
Your Answer: Capture in source application

Multiple Choice Single Answer


Question: Dimensionality reduction reduces the data set size by removing :-
Correct Answer: Irrelevant attributes
Your Answer: Irrelevant attributes

Multiple Choice Single Answer


Question: Maintenance of cache consistency is the limitation of :-
Correct Answer: MPP
Your Answer: NUMA

Select The Blank


Question: ________ is the method used to predict the value of response variable from one to
more variables.
Correct Answer: Regression
Your Answer: Analysis of variance

True/False
Question: Metadata is building block of data warehouse.
Correct Answer: True
Your Answer: True

Select The Blank

Page 75 of 89
SCDL – 4th Semester – Data Mining

Question: ________ is the type of pilot for early delivery with broader scope and may be
integrated.
Correct Answer: Broad business pilot
Your Answer: Broad business pilot

Select The Blank


Question: In data ________, data encoding or transformations are applied to obtain reduced or
compressed representation.
Correct Answer: Compression
Your Answer: Compression

Multiple Choice Multiple Answer


Question: Metadata in a data warehouse falls into following categories :-
Correct Answer: Operational Metadata , Extraction and Transformation metadata , End-user
Metadata
Your Answer: Operational Metadata , Extraction and Transformation metadata , End-user
Metadata

True/False
Question: Data integration merges data from multiple sources into coherent sources.
Correct Answer: True
Your Answer: True

Match The Following


Question Correct Answer Your Answer
Administration Providing support for all DBA functions Support for System administration
Extensibility Hybrid Extension to OLAP Providing support for all DBA database
functions
Portability Across platform APIs For tools from loading vendors
Query tool APIs For tools from loading Hybrid Extension to OLTP database
vendors

Multiple Choice Multiple Answer


Question: Data transformation includes :-
Correct Answer: Smoothing , Aggregation , Generalization
Your Answer: Smoothing , Aggregation , Generalization

Multiple Choice Multiple Answer


Question: Knowledge discovery process includes :-
Correct Answer: Data Cleaning , Data Intergration , Data Selectin
Your Answer: Data Cleaning , Data Intergration , Data Selectin

Multiple Choice Single Answer


Question: Queries run faster to find exact match using which type of indexing?
Correct Answer: Clustered index
Your Answer: Clustered index

True/False
Question: Intelligent miner is an IBM data mining product.
Correct Answer: True
Your Answer: True

LIST OF ATTEMPTED QUESTIONS AND ANSWERS

Multiple Choice Multiple Answer


Question: Building blocks of Data Warehouse are :-

Page 76 of 89
SCDL – 4th Semester – Data Mining

Correct Answer: Management and Control , Source Data , Data Staging


Your Answer: Management and Control , Source Data , Data Staging

Multiple Choice Single Answer


Question: Substantial portion of available information is stored in :-
Correct Answer: Text data
Your Answer: Object oriented database

True/False
Question: The data Warehouse is query-centric.
Correct Answer: True
Your Answer: True

True/False
Question: Data mining is a piece of integrated solutions.
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: Which of the following data capture method of data abstraction is time consuming?
Correct Answer: Capture by comparing files
Your Answer: Capture by comparing files

Select The Blank


Question: ________ does not handle categorical attributes.
Correct Answer: CURE
Your Answer: CURE

True/False
Question: In the data acquisition area, the data flow begins at the data sources and pauses at
staging area.
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: Association rules mining is based on :-
Correct Answer: Clustering and Employing rules for classification
Your Answer: Clustering and Employing rules for classification

True/False
Question: In physical design of warehouse, developing standard ensures consistency across
the various areas.
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: Bayes Theorem is :-
Correct Answer: P(H|X)=P(X|H)(P)/P(X)
Your Answer: P(H|X)=P(X|H)(P)/P(X)

Select The Blank


Question: Indexed ________ engines search index,web pages and build huge keyword based
indices which help to search sets of web pages containing certain keywords
Correct Answer: Web Search
Your Answer: Web Search

Page 77 of 89
SCDL – 4th Semester – Data Mining

Multiple Choice Single Answer


Question: Data matrix is :-
Correct Answer: Object by variable structure
Your Answer: Object by variable structure

Multiple Choice Single Answer


Question: Real world databases are highly susceptible to noisy, missing and inconsistent data
due to :-
Correct Answer: Huge size of data
Your Answer: Huge size of data

Multiple Choice Single Answer


Question: Simple matching approach is used for computing disimilarity between two objects for :-
Correct Answer: Nominal variable
Your Answer: Nominal variable

Multiple Choice Multiple Answer


Question: Clustering Techniques organised into following categories :-
Correct Answer: Partitioning , Density Based , Grid Based
Your Answer: Partitioning , Density Based , Grid Based

Select The Blank


Question: Most of the warehouses employ ________ database Management System.
Correct Answer: Relational
Your Answer: Relational

Multiple Choice Single Answer


Question: Data cleansing effort can begin with :-
Correct Answer: High priority data
Your Answer: High priority data

True/False
Question: Sequential pattern analysis and similarity search techniques have been developed in
data mining.
Correct Answer: True
Your Answer: True

Match The Following


Question Correct Answer Your Answer
Load Utility High performance data High performance data loading,
loading, recovery recovery
Query Governer Abort runaway query Abort runaway query
Query Optimizer Parsing, optimizing query Parsing, optimizing query
Query Management Balancing extraction of query Balancing extraction of query

Multiple Choice Multiple Answer


Question: Distinguishing characteristics of data warehouse architecture are :-
Correct Answer: Different Objective Scope , Data Content, Flexible and Dynamic
Your Answer: Different Objective Scope , Data Content , Flexible and Dynamic

Multiple Choice Single Answer


Question: Which type of integrity constraint forces the establishment of parent -child
relationship?
Correct Answer: Referential integrity
Your Answer: Referential integrity

Page 78 of 89
SCDL – 4th Semester – Data Mining

Select The Blank


Question: An information measures called ________ can be used to recursively partition the
values of numeric attribute.
Correct Answer: Entropy
Your Answer: Entropy

True/False
Question: Metadata is building block of data warehouse.
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: In which of the following type of mining frequently
occuring patterns related to time and sequence are mined?
Correct Answer: Sequential pattern mining
Your Answer: Time series data mining

Select The Blank


Question: ________ is the time consuming and less feasible approach for filling missing values.
Correct Answer: Filling missing values manually
Your Answer: Filling missing values manually

Multiple Choice Multiple Answer


Question: Classification and Prediction have following applications :-
Correct Answer: Credit approval , Medical Diagnosis, Performance Prediction
Your Answer: Credit approval , Medical Diagnosis , Performance Prediction

Multiple Choice Multiple Answer


Question: Data processing techniques are :-
Correct Answer: Cleansing , Integration , Transformation
Your Answer: Cleansing , Integration , Transformation

True/False
Question: Data in warehouse is primarily for query.
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: Data reduction obtains a reduced representation of
data set that is :-
Correct Answer: Much smaller
Your Answer: Much smaller

Multiple Choice Single Answer


Question: Which of the following type executes query
operations in pipeline manner?
Correct Answer: Vertical parallelism
Your Answer: Vertical parallelism

Multiple Choice Single Answer


Question: User gets an enterprise wide view of information
from the data warehouse due to :-
Correct Answer: Improved productivity
Your Answer: Newer opportunity

Select The Blank

Page 79 of 89
SCDL – 4th Semester – Data Mining

Question: ________ databases are one of the most poplularly


available and rich information repositories.
Correct Answer: Relational
Your Answer: Relational

Multiple Choice Single Answer


Question: Which database type stores a large amount of space-related data?
Correct Answer: Spatial
Your Answer: Spatial

Multiple Choice Multiple Answer


Question: DNA sequences are comprised of :-
Correct Answer: Adenine , Gaunine , Thymine
Your Answer: Adenine , Gaunine , Thymine

Multiple Choice Multiple Answer


Question: The strategies for data reduction are :-
Correct Answer: Data aggregation , Dimension reduction , Numerocity reduction
Your Answer: Data aggregation , Dimension reduction , Numerocity reduction

Select The Blank


Question: ________ is an effective way to discover knowledge from huge amount of data.
Correct Answer: Visual data mining
Your Answer: Web mining

Select The Blank


Question: ________ is the process of grouping data into classes.
Correct Answer: Clustering
Your Answer: Classification

Multiple Choice Multiple Answer


Question: Data mining Functionalities are :-
Correct Answer: Charactrization and Discrimination, Association Analysis, Cluster Analysis
Your Answer: Charactrization and Discrimination , Association Analysis , Cluster Analysis

Select The Blank


Question: ________ is a summarization of general characteristics or features of a target class of
data.
Correct Answer: Data Characterization
Your Answer: Data Characterization

Multiple Choice Single Answer


Question: Classification rules are extracted from
Correct Answer: Decision Tree
Your Answer: Decision Tree

Multiple Choice Single Answer


Question: Which of the follwing inheritance is supported by Object oriented databases?
Correct Answer: Multiple Inheritance
Your Answer: Single Inheritance

Select The Blank


Question: For decision making process ________ process which considers finding only
interesting patterns is used.
Correct Answer: Microeconomic view
Your Answer: Pattern discovery

Page 80 of 89
SCDL – 4th Semester – Data Mining

Match The Following


Question Correct Answer Your Answer
Initial load of data as-is' data capture as-is' data capture
warehouse
Static data Capture of data in given Capture of data in given point of point of
time time
Data revision Incremental data capture Incremental data capture
Incremental data Differed data capture Differed data capture

True/False
Question: Business metadata is like a roadmap or easy to use information directory showing
contents and how to get there.
Correct Answer: True
Your Answer: True

True/False
Question: Data in data warehouse cuts across application.
Correct Answer: True
Your Answer: True

True/False
Question: Remote deployment of desktop tools is usually faster.
Correct Answer: True
Your Answer: False

Multiple Choice Single Answer


Question: Effect of one attibute value on a given class is independent of values of other attibute
is called
Correct Answer: Value independence
Your Answer: Value independence

LIST OF ATTEMPTED QUESTIONS AND ANSWERS

Multiple Choice Multiple Answer


Question: Building blocks of Data Warehouse are :-
Correct Answer: Management and Control , Source Data , Data Staging
Your Answer: Management and Control , Source Data , Data Staging

Multiple Choice Single Answer


Question: Substantial portion of available information is stored in :-
Correct Answer: Text data
Your Answer: Object oriented database

True/False
Question: The data Warehouse is query-centric.
Correct Answer: True
Your Answer: True

True/False
Question: Data mining is a piece of integrated solutions.
Correct Answer: True
Your Answer: True

Page 81 of 89
SCDL – 4th Semester – Data Mining

Multiple Choice Single Answer


Question: Which of the following data capture method of data abstraction is time consuming?
Correct Answer: Capture by comparing files
Your Answer: Capture by comparing files

Select The Blank


Question: ________ does not handle categorical attributes.
Correct Answer: CURE
Your Answer: CURE

True/False
Question: In the data acquisition area, the data flow begins at the data sources and pauses at
staging area.
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: Association rules mining is based on :-
Correct Answer: Clustering and Employing rules for classification
Your Answer: Clustering and Employing rules for classification

True/False
Question: In physical design of warehouse, developing standard ensures consistency across the
various areas.
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: Bayes Theorem is :-
Correct Answer: P(H|X)=P(X|H)(P)/P(X)
Your Answer: P(H|X)=P(X|H)(P)/P(X)

Select The Blank


Question: Indexed ________ engines search index,web pages and build huge keyword based
indices which help to search sets of web pages containing certain keywords
Correct Answer: Web Search
Your Answer: Web Search

Multiple Choice Single Answer


Question: Data matrix is :-
Correct Answer: Object by variable structure
Your Answer: Object by variable structure

Multiple Choice Single Answer


Question: Real world databases are highly susceptible to noisy, missing and inconsistent data
due to :-
Correct Answer: Huge size of data
Your Answer: Huge size of data

Multiple Choice Single Answer


Question: Simple matching approach is used for computing disimilarity between two objects for :-
Correct Answer: Nominal variable
Your Answer: Nominal variable

Multiple Choice Multiple Answer

Page 82 of 89
SCDL – 4th Semester – Data Mining

Question: Clustering Techniques organised into following categories :-


Correct Answer: Partitioning , Density Based , Grid Based
Your Answer: Partitioning , Density Based , Grid Based

Select The Blank


Question: Most of the warehouses employ ________ database Management System.
Correct Answer: Relational
Your Answer: Relational

Multiple Choice Single Answer


Question: Data cleansing effort can begin with :-
Correct Answer: High priority data
Your Answer: High priority data

True/False
Question: Sequential pattern analysis and similarity search
techniques have been developed in data mining.
Correct Answer: True
Your Answer: True

Match The Following


Question Correct Answer Your Answer
Load Utility High performance data High performance
loading, recovery data loading, recovery
Query Governer Abort runaway query Abort runaway query
Query Optimizer Parsing, optimizing query Parsing, optimizing query
Query Management Balancing extraction of query Balancing extraction of query

Multiple Choice Multiple Answer


Question: Distinguishing characteristics of data warehouse architecture are :-
Correct Answer: Different Objective Scope, Data Content, Flexible and Dynamic
Your Answer: Different Objective Scope, Data Content, Flexible and Dynamic

Multiple Choice Single Answer


Question: Which type of integrity constraint forces the establishment of parent -child
relationship?
Correct Answer: Referential integrity
Your Answer: Referential integrity

Select The Blank


Question: An information measures called ________ can be used to recursively partition the
values of numeric attribute.
Correct Answer: Entropy
Your Answer: Entropy

True/False
Question: Metadata is building block of data warehouse.
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: In which of the following type of mining frequently occuring patterns related to time
and sequence are mined?
Correct Answer: Sequential pattern mining
Your Answer: Time series data mining

Page 83 of 89
SCDL – 4th Semester – Data Mining

Select The Blank


Question: ________ is the time consuming and less feasible approach for filling missing values.
Correct Answer: Filling missing values manually
Your Answer: Filling missing values manually

Multiple Choice Multiple Answer


Question: Classification and Prediction have following applications :-
Correct Answer: Credit approval , Medical Diagnosis, Performance Prediction
Your Answer: Credit approval , Medical Diagnosis , Performance Prediction

Multiple Choice Multiple Answer


Question: Data processing techniques are :-
Correct Answer: Cleansing , Integration , Transformation
Your Answer: Cleansing , Integration , Transformation

True/False
Question: Data in warehouse is primarily for query.
Correct Answer: True
Your Answer: True

Multiple Choice Single Answer


Question: Data reduction obtains a reduced representation of data set that is :-
Correct Answer: Much smaller
Your Answer: Much smaller

Multiple Choice Single Answer


Question: Which of the following type executes query operations in pipeline manner?
Correct Answer: Vertical parallelism
Your Answer: Vertical parallelism

Multiple Choice Single Answer


Question: User gets an enterprise wide view of information from the data warehouse due to :-
Correct Answer: Improved productivity
Your Answer: Newer opportunity

Select The Blank


Question: ________ databases are one of the most poplularly available and rich information
repositories.
Correct Answer: Relational
Your Answer: Relational

Multiple Choice Single Answer


Question: Which database type stores a large amount of space-related data?
Correct Answer: Spatial
Your Answer: Spatial

Multiple Choice Multiple Answer


Question: DNA sequences are comprised of :-
Correct Answer: Adenine , Gaunine , Thymine
Your Answer: Adenine , Gaunine , Thymine

Multiple Choice Multiple Answer


Question: The strategies for data reduction are :-
Correct Answer: Data aggregation , Dimension reduction ,Numerocity reduction
Your Answer: Data aggregation , Dimension reduction , Numerocity reduction

Page 84 of 89
SCDL – 4th Semester – Data Mining

Select The Blank


Question: ________ is an effective way to discover knowledge from huge amount of data.
Correct Answer: Visual data mining
Your Answer: Web mining

Select The Blank


Question: ________ is the process of grouping data into classes.
Correct Answer: Clustering
Your Answer: Classification

Multiple Choice Multiple Answer


Question: Data mining Functionalities are :-
Correct Answer: Charactrization and Discrimination, Association Analysis , Cluster Analysis
Your Answer: Charactrization and Discrimination, Association Analysis , Cluster Analysis

Select The Blank


Question: ________ is a summarization of general characteristics or features of a target class of
data.
Correct Answer: Data Characterization
Your Answer: Data Characterization

Multiple Choice Single Answer


Question: Classification rules are extracted from
Correct Answer: Decision Tree
Your Answer: Decision Tree

Multiple Choice Single Answer


Question: Which of the follwing inheritance is supported by Object oriented databases?
Correct Answer: Multiple Inheritance
Your Answer: Single Inheritance

Select The Blank


Question: For decision making process ________ process which considers finding only
interesting patterns is used.
Correct Answer: Microeconomic view
Your Answer: Pattern discovery

Match The Following


Question Correct Answer Your Answer
Initial load of data warehouse as-is' data capture as-is' data capture
Static data Capture of data in given Capture of data in given point
point of time time
Data revision Incremental data capture Incremental data capture
Incremental data capture Differed data capture Differed data capture

True/False
Question: Business metadata is like a roadmap or easy to use information directory showing
contents and how to get there.
Correct Answer: True
Your Answer: True

True/False
Question: Data in data warehouse cuts across application.
Correct Answer: True
Your Answer: True

Page 85 of 89
SCDL – 4th Semester – Data Mining

True/False
Question: Remote deployment of desktop tools is usually faster.
Correct Answer: True
Your Answer: False

Multiple Choice Single Answer


Question: Effect of one attibute value on a given class is independent of values of other attibute
is called
Correct Answer: Value independence
Your Answer: Value independence

Unattended Questions
Match the Following
. Data Quality tool 1. Assist data ware house administration
2
2. OLAP tools 2. Locating data errors
6
3. Alert system tool 3. Transparent access to source system
5
4. Middleware & connectivity tool 4. Track on number of queries
3
5. Users attention on exceptions
6. Channel queries

Select The Blank

clustering method follows statistical and neural network


approach.

True/False
Data cleansing means removing noisy and inconsistent data. TRUE

Match The Following


1. Non volatile data 2 1. External data

2. Data granularity 4 2. Query and analysis


3. Data from external source 1 3. Production data
4. Disparate data 3 4. Level of detail
5. Archive data
6. Internal data

Match The Following


1. Data storage 1 1. Data management

2. Data staging 2 2. Workbench for data


3. Data Mining 5 3. Details of summary

Page 86 of 89
SCDL – 4th Semester – Data Mining

4. Metadata 6 4. Private spreadsheet data


5. Knowledge discovery
6. Roadmap for user

True/False
The Structure that brings all the components together is known as Architecture.
TRUE/FALSE

Match The Following


1. Data modeling tool 1 1. Reverse Engineering capabilities

2. Data Extraction tool 4 2. Default values


3. Data transformation tool 2 3. Formulating and running queries
4. Data loading tool 5 4. Bulk extraction for full refresh
5. Primary key generation
6. Replication

Match The Following


1. Static data 1. Immediate data capture

2. Data revision 2. Capture of data in given point of time

3. Incremental data capture 3. Incremental data capture

4. Initial load of data warehouse 4. Value of attribute at specific time

5. "as-is" data capture


6. Differed data capture

Match The Following


1. Initial Load 1. New record supercedes
4
2. Incremental Load 2. Offline data warehouse
6
3. Load Image 3. Applying data
5
4. Constructive merge 4. Populating data warehouse table first time
1
5. To correspond to target files
6. Applying ongoing changes

Match The Following

Page 87 of 89
SCDL – 4th Semester – Data Mining

1. Identify source application 2 1. Method of extraction

2. Denote time window 5 2. Source identification


3. Handling unextractable input records 6 3. Extraction
4. Extraction is manual/Tool based 1 4. Job sequencing
5. Time window
6. Exception handling

Multiple Choice Multiple Answer


7. The main categories of Metadata in warehouse are :-
a)
Operational
b)
Execution and Transformation Metadata
c)
Extraction and transformation Metadata
d)
End user Metadata

Multiple Choice Multiple Answer


20.The ways of Intra query parallelization are :-

a)
Horizontal parallelization
b)
Vertical Parallelization
c)
Hybrid parallelization
d)
Homogenous parallelization

Multiple Choice Single Answer


30.Sequence of physical design of data warehouse is :-

a)
Develop standards--Create aggregate plans--determine data partitioning schemem--extablish
b) clustering option--prepare indexing strategy--complete physical model
c)
Develop standards--determine data partitioning scheme--Create aggregate plans--establish
d) clustering option--prepare indexing strategy--complete physical model

Develop standards--prepare indexing strategy--Create aggregate plans--determine data


partitioning scheme--establish clustering option---complete physical model

Develop standards--Create aggregate plans--establish clustering option--determine data


partitioning scheme--prepare indexing strategy--complete physical model

Multiple Choice Single Answer


44.Data migration affects performance requiring multiple blocks to be read which can be
adjusted by :-

Page 88 of 89
SCDL – 4th Semester – Data Mining

a)
Block percent free
b)
Block percent used
c)
Block percent occupied
d)
Block percent vacant

True/False
48. In Linear regression data are modeled to fit a straight line.

True

False

Select The Blank


16. The technique of_____________enables concurrent input/output operations and improves
file's access performance substantially.
a) Data migration
b) File striping
c) Block utilization
d) Dynamic extension

Match the Following


1. Data visualization 1. Visual display

2. Data mining result visualization 2. Presentation of knowledge

3. Data mining process visualization 3. Data mining in visual format

4. Interactive visual data mining 4. Visualization tool

5. Graphical display
6. Audio signal

Page 89 of 89