DECISION SUPPORT SYSTEM

Decision Support Systems

Decision support systems (DSS)
Offer potential to assist in solving both semistructured and unstructured problems

Decision Support in Business

Companies invest in data-driven decision support application frameworks to help them respond to Changing marketing conditions Customer needs

Management information Accomplished by several types of Decision support Other information systems

Decision Structure
Structured (operational) The procedures to follow when a decision is needed can be specified in advance It is not possible to specify in advance most of the decision procedures to follow Decision procedures can be pre-specified, but not enough to lead to the correct decision

Unstructured (strategic)

Semi-structured (tactical)

Information Quality
Information products are made more valuable by their attributes, characteristics, or qualities Outdated, inaccurate, or hard to understand information has much less value Information has three dimensions Time Content Form

Attributes of Information Quality

Decision Support Trends

Personalized decision support

Modeling

Information retrieval

Data warehousing

What-if scenarios

Reporting

Decision Support Trends

Business Intelligence Applications

Difference between DSS- BI connection

Business Intelligence BI is more appropriate for large organizations (DWH is expensive) BI implies to use data warehouse. It provide accurate and timely information and support DSS. It has an executive & strategy orientation, especially in BPM and dashboards Decision Support System DSS can be appropriate to any type of organization. DSS may or may not have such feature. DSS are constructed to directly support specific decision making. DSS is oriented towards analysts.

Business Intelligence BI is constructed with commercial available tools and components.

Decision Support System They may have constructing solutions to very unstructured problem. In this more programming may be needed to customize solution. DSS methodologies & even some tools were developed mostly in academic world.

BI methodologies and tools were developed mostly by software companies.

Decision Making as a Component of Problem Solving

Intelligence Decision making

Design Problem solving

Choice

Implementation

Monitoring

Solution Types
Optimization model
Finding the best solution

Satisficing model
Finding a good -- but not necessarily the best - solution to a problem

Heuristics
Commonly accepted guidelines or procedures that usually find a good solution

Problem Solving Factors

Multiple decision objectives Increased alternatives Increased competition The need for creativity Social and political actions International aspects Technology Time compression

Characteristics of a DSS (1)

Handles large amounts of data from different sources Provides report and presentation flexibility Offers both textual and graphical orientation

Characteristics of a DSS (2)

Supports drill down analysis Performs complex, sophisticated analysis and comparisons using advanced software packages Supports optimization, satisfying, and heuristic approaches

Characteristics of a DSS (3)

Performs different types of analyses
What-if analysis
Makes hypothetical changes to problem and observes impact on the results

Simulation
Duplicates features of a real system

Goal-seeking analysis
Determines problem data required for a given result

Goal Seeking Example

You know the desired result You want to know the required input(s) Example:
Microsoft Excels Goal Seek and Solver functions

Capabilities of a DSS (1)

Supports
Problem solving phases Different decision frequencies

Merge with another company?

How many widgets should I order?

low

high

Capabilities of a DSS (2)

Highly structured problems
Straightforward problems, requiring known facts and relationships.

Semi-structured or unstructured problems

Complex problems wherein relationships among data are not always clear, the data may be in a variety of formats, and are often difficult to manipulate or obtain

Standalone Integration and Web- based

Semi structured and Unstructured problems

Support managers at all levels

Data access

Support individuals and groups

Modeling and analysis

Interdependent or Sequential decisions

DSS
Ease of development by end users Support Intelligence, design, choice, implementation Support variety Of decision processes and styles Effectiveness, not efficiency Interactive ease of use Adaptable and flexible

Human control the process

Decision Making Levels

Strategic Tactical Operational High Operational-level managers involved with daily decisions

Strategic-level managers involved with long-term decisions

Low Decision Frequency

Integration of TPS, MIS, and DSS

In many organizations they are integrated through a common database Separation of DSS transactions in the database from TPS and MIS transactions may be important for performance reasons

DIFFERENCE BETWEEN MIS AND DSS

Management Information Systems Decision support provided Information form and frequency Information format Information processing methodology Provide information about the performance of the organization Periodic, exception, demand, and push reports and responses Pre-specified, fixed format Information produced by extraction and manipulation of business data Decision Support Systems Provide information and techniques to analyze specific problems Interactive inquiries and responses Ad hoc, flexible, and adaptable format Information produced by analytical modeling of business data

Web-Based Decision Support Systems

Web-based decision support systems
Decision support system software provides business intelligence through web browser clients that access databases either through the Internet or a corporate intranet

DSS Components

Components of a DSS
Model management software (MMS)
Coordinates the use of models in the DSS

Model base
Provides decision makers with access to a variety of models

Dialogue manager
Allows decision makers to easily access and manipulate the DSS

Database

Model base

DBMS

MMS

Access to the internet, networks, and other computer systems

External database access

External databases

Dialogue manager

Model Base
Model Base
Provides decision makers with access to a variety of models and assists them in decision making

Models
Financial models Statistical analysis models Graphical models Project management models

Advantages and Disadvantages of Modeling

Advantages

Less expensive than custom approaches or real systems. Faster to construct than real systems Less risky than real systems Provides learning experience (trial and error) Future projections are possible Can test assumptions

Disadvantages

Assumptions about reality may be incorrect Accuracy of predications often unreliable Requires abstract thinking

TYPES of DSS

Objectives
Describe seven basic types of DSS. Discuss different categories of DSS.
Based on support Based on nature of decision situation Based on number of users

Understand where different types of DSS fit into Simons model of decision making.

The DSS Hierarchy

Suggestion systems Optimization systems Representational models Accounting models Analysis information systems Data analysis systems File drawer systems

File Drawer Systems

They are the simplest type of DSS Can provide access to data items Data is used to make a decision ATM Machine Use the balance to make transfer of funds decisions

Data Analysis Systems

Provide access to data Allows data manipulation capabilities Airline Reservation system No more seats available Provide alternative flights you can use Use the info to make flight plans

Analysis Information Systems

Information from several files are combined Some of these files may be external We have a true data base The information from one file, table, can be combined with information from other files to answer a specific query.

Accounting Models
Use internal accounting data Provide accounting modeling capabilities Can not handle uncertainty Use Bill of Material
Calculate production cost Make pricing decisions

Representational Model
Can incorporate uncertainty Uses models to solve decision problem using forecasts Can be used to augment the capabilities of Accounting models Use the demand data to forecast next years demand Use the results to make inventory decisions.

Optimization Systems
Used to estimate the effects of different decision alternative Based on optimization models Can incorporate uncertainty Assign sales force to territory Provide the best assignment schedule

Suggestion Systems
A descriptive model used to suggest to the decision maker the best action A prescriptive model used to suggest to the decision maker the best action May incorporate an Expert System Use the system to recommend a decision Ex: Applicant applies for personal loan

DSS Categories
Support-based categories (Alter 1980)
Data-based DSS Model-based DSS

Nature of the decision situation (Donovan & Madnick 1977)

Institutional Ad hoc

User-based categories (Keen 1980)

Individual Multi-individual Group

DSS Categories
Support based DSS
Data-based DSS Model-based DSS

Structured Model-based DSS

Semi-structure Data-based DSS

Unstructured

DSS Categories
Based on the nature of the decision situation
Institutional
Culture of the organization Regularly used Used by more than one persons

Ad hoc
One of kind One-time use Used by single individual

DSS Categories
Based on number of users
Individual Multi-individual Group
Benefits
Improving personal efficiency Expediting problem solving Facilitating communication Promoting learning Increasing control

Individual H L L M L

Multi- Group individual H L M L H H H H H M

Simons Model
External Internal Intelligence AI, EIS

Problem Identification

ES Design

Qualitative Analysis

DSS

Quantitative Analysis

DbDSS, MbDSS

GDSS

Choice

Decision

ES

Usage Modes
Subscription Mode Terminal Mode Clerk Mode Intermediary Mode

Subscription Model
Decision maker receives outputs from the DSS on regular basis

Terminal Mode
Direct use of the DSS by the decision maker Access is through individual terminals May be user specific requirements

Clerk Mode
Decision maker fills out a form requesting output from DSS A clerk accesses the DSS Sends the output to the decision maker

Intermediary Mode
Decision maker uses the DSS with the help of a professional, knowledgeable assistant The assistant can be either a:
Staff Assistant Technical Support Staff Business Analyst

Group Decision Support and Groupware Technologies

Objectives
Understanding of making decisions under the environment of multipaticipants (M) Gain understanding of different support technologies under group support environment Introduction to MDM classification Common methods of MDM

(p3)

Definition of multiparticipants
Refers as:
a collection of entity of more than one individual participant in decision making process Generally, it also refers as group, which is independent of the properties (ie characteristics) of its members
(p4)

Multiparticipant Decision Making

denotes as MDM is an activity conducted by a group as well as its individual members its structure is primarily based on the interaction and flow of communication among its members
(p5)
Question: Do you think if an Enterprise Resources Planning system is a MDM system? Why yes or not?

Two different branches on how MDM is structured: 1) Collaborative structure

refers as multiple decision makers with complete interaction, that is by Group-based

2) Non-collaborative structure
refers single decision maker with/without complete participant interaction Committee
(p6)

Team
(p7)

Figure 6-2 refers to its direction and structure of them

Basic MDM Structures

Group
Multiple DMs with complete interaction

Team
Single DM with no participant interaction

Committee
Single DM with complete participant interaction

Dimensions of direction flow of each structure

6

(p5)

Basic types of Group communication network

4 Basic types: 1. The wheel 2. The chain 3. The circle 4. The completely connected network
(p8) (p9) (p10) (p11)

Their network structure The degree of their centrality

(p13)

(p14) (p15) 7

The Wheel Network

Most structured and hierarchical of four types best refer to team (why?) each participant can only communicate with decision maker; but not within those participants more appropriate when routine and recurring decisions are being made; where time and cost are priorities mainly unsatisfying by participants (why?)
(p7)

The Chain Network

Mainly focus on the decision maker is a relay system where each participant receives information from one participant and sends it to another the decision maker is direct/indirect contact with all participants the end participant(s) has the less satisfying (why?)
(p7)

The Circle Network

All members provide equal opportunity for communication all members receive all information and also serve as a decision makers all members are satisfying (why?) serves well for the Group and Committee MDM structure; where negotiation or consensus is a basis of the final decision
(p7)

10

The Completely Connected Network

Completely free communication and interaction among the members information takes longer to convey and much error and message distortion (why?) is a true Group structure MDM

(p7)

11

Hierarchical Classification of MDM Structures

Decision Structure

Collaborative
Communication among non-decisionmakers is relevant

Non-Collaborative
Communication among non-decisionmakers is irrelevant

Group
Formal Participants Multiple Decision-makers

Team
Formal Participants Single Decision-maker

Individual
No formal sources Single Decision-maker

Consensus
All must agree

Majority
Stated % must agree

Collective communication between participants & Decision-maker

Committee

Interactive communication between non-decision-maker participants

Consensus
All must agree

Majority
Stated % must agree

Results directly from decision

Implementation

Results directly from recommendation

12

Basic Communication Network Structures

Wheel Network

Circle Network

(p7)
Chain Network Completely Connected Network

13

Principal Characteristics of Network Structures

Highly Centralized Wheel, Chain
Efficient for routine and recurring decisions They tend to strengthen the leadership position of the central members They tend to result in a stable set of interaction among the participants They tend to produce lower levels of satisfaction among the participants

Highly Decentralized Circle, Completely Connected

They tend to produce higher levels of satisfaction among the participants They facilitate non-routine or nonrecurring decisions They promote innovative and creative solutions
(p7) Question: Is it true that one of these methods always outperformed the other?
14

Which MDM structure should be adopted?

refer to Table 6-3(p16) a complete explanation refers to Table 6-2(p17)

(p18) 15

Matrix for MDM Structure Selection

Single DM

Individual Factors
High Importance DM Expertise Participant Expertise High Structuredness Acceptance Critical Acceptance Probable Participant Motivation Potential for Conflict

Team

Committee

Group

(p15)

16

Factors Used in Determining Decision Structure

The importance of the quality of the decision The extent to which the DM possesses the knowledge and expertise to make the decision The extent to which potential participants have the necessary information The degree of structuredness of the problem context The degree to which acceptance or commitment is critical to successful implementation The probability of acceptance The degree of motivation among the participants to achieve organizational goals The degree of potential conflict among the participants
(p15)

17

Problems associated to MDM?

Size of MDM (p19) Group think(p20) Other Sociological issues (p21)
Note: Here, these problems are referred to a DMD environment with or without the use of simple or conventional information systems.

(p22)

How to solve these problems?

18

Effects Related to MDM Size

Ex: Insufficient time in a short meeting

Participant interaction tends to decrease with Dispute takes place because some might fell increase in size being left out Affective or emotional relationships tend to decrease with increase in size Central, dominant leadership tends to increase with size Such as juniors affair to speak their minds Conflict is resolved with political rather than analytical solutions as size increases
(p18)

This may due to above events and that most cases the decision will then be followed the present policy to determine the current problems 19

Potential Consequences of Groupthink

Tends to preclude a complete and open-minded analysis of opportunities in the development of objectives Inhibits a meaningful search for information and tends to bias any searches toward a self-fulfilling selectivity Limits the participants ability to impartially appraise alternatives Often results in a complete failure to consider possibilities associated with cost of failure which, in turn, tends to result in choice selections that are more risky than is warranted by the payoff. Tends to eliminate the formation of contingency or fallback positions

(p18)

20

Sociological issues
1. Conflict
occurs in the reduced effectiveness of MDM choice outcomes

2. Participant Anonymity
used to control sources of potential conflict and in support of other MDM processes

3. Gender Differences and Similarities

significant differences in perceived or expected performance across genders
(p18)

21

Basic Levels of MDM Support Technology

Four categories, Table 6-5 (p23) 1. Decision Support Systems (DSS)
a system typically used by one or more DM

2. Group Decision Support Systems (GDSS)

design to support the activities for decision making

3. Group Support and Groupware (GSS)

efforts direct to identifying and solving problems/issues (but assistance may not be available)

(p24)

4. Organizational Decision Support System (ODSS)

enterprise-wide comm/collaboration

(p27)

22

MDM Support Technology Categorization

DSS

(p22)

23

Groupware Classification
Messaging systems Conferencing systems Collaborative authoring systems Group decision support systems Coordination systems Intelligent agent systems

(p25)

24

Forces In Favor of Groupware Adoption

Increased cost control Increased productivity Improved customer service Support for total quality management (TQM) activities Reduced number of meetings Increased automation of routine workflow processes Desire to extend the organization to include both supplier and customer Need to integrate geophysically dislocated teams Increased competitive advantage through faster time to market Need for better global coordination Creation of services that differentiate the organization Leveraging of professional expertise and knowledge Availability of widespread network infrastructures (i.e., Internet, WWW) Improved price/performance ratios of both hardware and software necessary Increased use of ad hoc teams (p26)

25

Lotus Notes Groupware Typical Desktop Layout

Component Applets Palette

Database Access Icons

Drop-down menus and SmartIcons

Workspace File Tabs

(p22)

26

MDM Classificiations

1. By Features(p28)
level one : reduce communication barriers level two: reduce uncertainty and noise level three: regulate decision process

2. By Technology (p29)
Electronic boardroom, Teleconference Room, Group Network, Information Center, Collaboration Laboratory, and Decision Room (p30)

(p31)

27

DeSanctis and Gallupe MDM System Classification

MDM Level Participant Needs
message passing among participants access to data files during meeting simultaneous display of ideas, graphs, votes, etc. to all participants relaxation of inhibitions to contribute control for free-riders organization and analysis of ideas and votes preference quantification agenda planning schedule coordination -

System Feature
Electronic messaging Computer networking Large shared viewing screen or public display window Anonymous contribution Active solicitation of ideas Summarization and tabulation Rating/ranking scales Agenda templates Continuous display of progress

1
Reduced
Communication Barriers

2
Reduce Uncertainty and Noise

problem structuring and solution scheduling uncertainty analysis analysis of resource allocation problems data analysis preference analysis structured guidance of deliberations

Automated planning methods (PERT, etc.) Decision tables, trees, etc. LP and optimization modeling Statistical tools Subjective probability methods MDM coordination methods (nominal, etc.)

3
Regulate Decision Processes

enforcement of formal decision procedures increased clarity of options for decision procedures structuring and filtering of messages to adhere to rules development of deliberation governance rules

Automated procedure mechanisms Automated advisor for providing advice regarding various approaches Structuring and filter agents Rule set construction and inference mechanisms

(p27)
28

Kraemer and King MDM Classification by Technology

M D M T ype
E le c tro n ic B o a r d ro o m

F a c ilit y a n d H a rd w a re
C o n f e r e n c e r o o m w it h c o m p u t e r -c o n t r o lle d a u d io v is u a l w id e - s c r e e n p r o je c t io n c a p a b ilit ie s C o n f e r e n c e r o o m w it h c o m p u t e r -c o n t r o lle d a u d io v is u a l t r a n s m is s io n b e t w e e n lo c a t io n s S e p a r a t e o ff ic e f a c ilit ie s c o n n e c t e d v ia a c o m p u t e r n e tw o rk

S o ftw a re
A p p lic a t io n f o r s t o r a g e a n d r e t r ie v a l o f p r e v io u s ly p r e p a r e d p r e s e n t a t io n s

S p e c ific C o n s id e r a tio n s
S a m e t im e -s a m e p la c e s y n c h r o n o u s in t e r a c t io n . R e q u ir e s a u d io v is u a l t e c h n ic ia n t o b e p r e s e n t S a m e t im e - d if f e r e n t p la c e s y n c h r o n o u s in t e r a c t io n . R e q u ir e s t e le c o n f e r e n c in g t e c h n ic ia n t o b e p r e s e n t S a m e t im e o r d if f e r e n t t im e d if f e r e n t p la c e in t e r a c t io n w it h o n e p a r t ic ip a n t s e r v in g a s c o o r d in a t o r o r c h a ir

T e le c o n fe re n c e R o o m

A p p lic a t io n t o c o n t r o l d ig it a l t r a n s m is s io n o f a u d io , v id e o , a n d d a t a

G r o u p N e tw o r k

A p p lic a t io n s t o a llo w f o r e it h e r r e a l- t im e o r a s y n c h ro n o u s d e s k to p c o n f e r e n c in g a n d e x c h a n g e o f v id e o , a u d io , a n d d a t a A p p lic a t io n s f o r d a t a b a s e m a n a g e m e n t , s t a tis t ic a l a n a ly s is , g r a p h ic s g e n e r a t io n , a n d w o r d p r o c e s s in g A p p lic a t io n s f o r c o lla b o r a t iv e in t e r a c t io n a n d in f o rm a t io n e x c h a n g e

In fo rm a tio n C e n te r

C o n f e r e n c e r o o m w it h v id e o p r o je c t o r f o r w id e - s c r e e n v ie w in g . I n d iv id u a l c o m p u t e rs w it h d is p la y t e rm in a ls C o n f e r e n c e r o o m w it h e le c t r o n ic w h it e b o a r d a n d n e t w o r k e d c o m p u t e rs

S a m e t im e -s a m e p la c e in t e r a c tio n . R e q u ir e s s p e c ia lis t s in m o d e lin g a n d s p e c if ic a p p lic a tio n s o f t w a r e to b e p re s e n t S a m e o r d iff e r e n t t im e s a m e p la c e in t e r a c t io n . R e q u ir e s M D M p r o c e s s f a c ilit a t o r t o b e p r e s e n t S a m e o r d iff e r e n t t im e s a m e p la c e in t e r a c t io n . R e q u ir e s M D M p r o c e s s f a c ilit a t o r t o b e p r e s e n t

C o lla b o r a tio n L a b o ra to r y

D e c is io n R o o m

C o n f e r e n c e r o o m w it h v id e o p r o je c t o r f o r w id e s c r e e n v ie w in g a n d n e t w o r k e d c o m p u t e rs

A p p lic a t io n s t o s u p p o r t b r a in s t o r m in g , t o p ic c o m m e n t a r y , v o t in g , m o d e lin g , d e c is io n a n a ly s is , c o lla b o r a t iv e in t e r a c t io n a n d d a ta e x c h a n g e

(p27)
29

Decision Room MDM Support Functions

Electronic brainstorming Topic commentary Issue analysis Voting and preference indication Policy formation Stakeholder analysis Organization of ideas Evaluation of alternatives Survey and Questionnaire creation and administration Multiple format file readers Participant dictionary Enterprise analysis of decision outcome on organization MDM session management
(P27)

30

Pros and Cons of MDM Activities

Sources of
Gains (p32) Losses
(p33)

(p34)

31

Sources of Gains in MDM Activities

Collective has greater knowledge than any single participant Allows for synergistic results otherwise not obtainable Interaction stimulates the generation of knowledge or information otherwise unavailable Participants can improve individual performance through learning from others Improved evaluation over individual decision-making structure

(p31)

32

Sources of Losses in MDM Activities

Relative allocation of speaking time is reduced with MDM size Can result in idea production blocking Can produce information overload much faster Participants may not be able to remember all the contributions of others Pressures resulting in conformity can be exacerbated Allows for free-riding or social loafing of lazy or non-participative individuals Can promote cognitive inertia or groupthink Increases opportunity for socialization over goal focus Increases decision context coordination activities Can allow for partial task or knowledge analysis
(p31)

33

Managing MDM Activities

1. Norminal Group Technique
like a brainstorming approach with revealing participants ideas with voting system

2. Delphi Technique
three round of information gathering

3. Issue-based Information Systems

hypertext-based linking of relevant issues

4. Arbitration
outside party serves as the arbitrator and select alternative from a set of feasible solutions
34

MDM Support Technology Variables

Contextual Variables
Personal Factors Attitude Abilities Individual motives Background

Task-related Outcomes
I. Characteristics of the decision Quality Variability of quality over time Breadth II. Implementation of the decision Cost Ease Commitment of participants III. Attitude of participants toward decision Acceptance Comprehension Satisfaction Confidence

Group Process
Situational Factors I. Situational Factors Reasons for group membership Stage in group development Existing social networks Background Depth of analysis Participation Consensus reaching Time to reach the decision II. Communication Characteristics Clarification efforts Efficiency of the communication Exchange of information Nonverbal communication Task-oriented communication III. Interpersonal characteristics Cooperation Domination of a few members IV. Structure imposed by the technology

Group structure Work group norms Power relationships Status relationships Group cohesiveness Density (group size, room size, interpersonal distance) Anonymity Facilitator

I. Attitude toward group process Satisfaction Willingness to work with participants in the future

Technological support Degree Type

Group-related Outcomes
Task characteristics Complexity Nature Degree of uncertainty

35

EXPERT SYSTEMS

Definition
According to Darlington:
An expert system is a program that attempts to mimic human expertise by applying inference methods to a specific body of knowledge.

According to Turban:
An expert system is a system that employs human knowledge captured in a computer to solve problems that ordinarily require human expertise.

Introduction to Expert Systems

Historically Expert Systems grew with AI, and can be regarded as a branch of AI.

Definition of AI
Artificial Intelligence (AI) is the part of computer science concerned with designing intelligent computer systems, that is, systems that exhibit the characteristics we associate with intelligence in human behavior understanding language, learning reasoning, solving problems and so on.
Barr and Feigenbaum, 1981

Introduction to Expert Systems

Initially, attempts were made to make computers intelligent in a general way. In 1960s Allan Newell and Herbert Simon wrote computer programs to test the hypothesis that intelligent behavior resulted from heuristic search.
GPS is aimed at finding general principles of intelligent problem solving.

Introduction to Expert Systems

It was quickly realized that the way to make progress was to focus on particular application domains, and expert systems started to appear. Early ones were
DENDRAL molecular structure of chemical compounds. MYCIN diagnosis of bacterial infections.

Introduction to Expert Systems

Pioneer work Herbert Simon, Allen Newell 1955 Carnegie Mellon Logic Theorist: proved theorems using propositional logic LISP

1960

Marvin Minsky John McCarthy Claude Shannon

MIT Dartmouth Bell Labs

Early Expert Systems

1960 DENDRAL Feigenbaum & Buchanan (Stanford) Stanford Identify chemical constituents diagnosis of infectious diseases Math expert system Speach recognition Mineral diagnosis Computer configuration

1970

MYCIN

1970 1970 1977 1978

MACSYMA HEARSAY PROSPECTOR XCON

MIT Carnegie Mellon Stanford Research Inst Duda, Hart, Barnett McDermott

Expert Systems
The term expert system is used in a seminal paper by Alan Turing in 1937 related to a study in AI. An Expert System (ES) is a computer program that reasons using knowledge to solve complex problems. (Feigenbaum, 1992) Traditionally, computers solve complex problems by arithmetic calculations; and the knowledge to solve the problem is only known by the human programmer.

Expert Systems
Expert systems are different from traditional application programs in that their capability to deal with challenging real world problems through the application process that reflect human judgment and intuition. Expert systems should not be confused with cognitive modeling programs, which attempt to simulate human mental architecture in detail. Expert systems are practical programs that use heuristic strategies developed to solve specific classes of problems.

Expert Systems Applications vs Conventional Systems Applications

Expert Systems Applications
Knowledge is fragmented and implicit, is difficult to communicate except in small chunks, and is often distributed amongst individuals who may disagree. Rules are complex, conditional and often defined as imprecise rules of thumb.

Conventional Systems Applications

Knowledge is complete and explicit, and is easily communicated with formulas and algorithms. Rules are simple with few conditions.

The finished system captures, The finished product automates distributes and leverages expertise manual procedures

Expert Systes Applications vs Conventional Systems Applications

Expert Systems Applications
Problem-solving demands dynamic, context-driven application of facts, relationship and rules System performance is measured in degrees of accuracy and completeness where explanations may be required to establish correctness.

Conventional Systems Applications

Problem-solving requires predictable and repetetive sequences of actions. Simple criteria are used to determine accuracy and completeness.

Some Concepts in Expert Systems and Conventional Systems

Expert Systems
Inferencing Knowledge Base Object Class Object Instance Object Attribute Rule

Conventional Systems Brief Comment

Program Flow Database Relational Table Relational Table Record Relational Table Field If.. Then Statement Inferencing is non-sequential Knowledge Base contains data and strategies Object structure is logical not physical Represents data only, not procedures Object attributes are inherited, not redefined Rule execution is not sequential

Expertise
Expertise is task-specific knowledge acquired and developed from training, reading and experience. It may consist of Facts, theories, rules, procedures. Guidelines (heuristics) based on intuition Strategies or approaches Meta knowledge Most organizations recognize the value of expertise but have difficulty in controlling or quantifying it. All individuals have expertise, but it is often unconscious, and there are different levels of expertise.

Expertise
There is more involved than just problem solving or reasoning. Also important are:
Storage of knowledge Dealing with complexity Representation of expertise Confidence in results

Experts
Experts are people who have uncommon expertise. To be useful, experts must have other qualities also. They should be able to
Recognize and formulate problems Explain Organize knowledge (make connections) Determine relevance Solve problems

We may regard such abilities as desirable in programs or systems which aim to be expert

Structure of an Expert System

An ES will normally have two aspects:
A development environment A consultation environment

The former is used by the system builder to modify the system. The later is used by the non-expert to obtain knowledge or advice. It is the latter which is thought of as an ES.

Structure of an Expert System

An ES is a program with various components:
1. 2. 3. 4. 5. 6. 7.

Knowledge acquisition subsystem Knowledge base Inference engine User interface Explanation subsystem Blackboard Knowledge refinement subsystem

The last two of these will not necessarily occur. We shall consider the others in more detail later.

Architecture of ES

The User Interface

The user of an ES can be a tester, a tutor, a pupil, or a customer. User Interface style could be menu-driven, question and answer, natural language or graphics interface User interface facilities are designed to recognize
The mode of the user The level of the users expertise Nature of the transaction

The User Interface

An ES may obtain input from an online data source (database,text file, web page, etc). An ES may be used to monitor a physical system, in which case input may come directly from sensing devices. An ES may be used to control a physical system, in which case output will be signals to the system. When interacting with humans, standard HCI (HumanComputer Interaction) concerns apply.

Knowledge-base
The power of problem solving is primarily the consequence of the knowledge base and secondarily on the inference method employed. A storehouse of knowledge primitives. The design of knowledge representation scheme impacts the design of the inference engine, the knowledge updating process, the explanation process and the overall efficiency of the system. Therefore the selection of the knowledge representation scheme is one of the most critical decision in ES design.

Components of the knowledge of the ES

Facts: Ex: Milk is white. Procedural rules: Well defined invariant rules that describe fundamental sequences of events and relations relative to the domain. ( Always check the traffic before merging onto the freeway.) Heuristic rules: Rules of thumb gained by experience. An expert also has a general conceptual model of the subject domain and an overall scheme for finding a solution.

Knowledge Update
Manual
by the knowledge engineer domain expert

Machine learning

Knowledge Engineering
Knowledge engineering is the process of acquiring specific domain knowledge and building it into the knowledge base. Knowledge extraction can be done by
interviews, observation of the expert at work, evaluation of the material used by the expert.

This process is termed knowledge acquisition. It involves problem definition, implementation, and refinement as well as representing facts and relations acquired from an expert.

Knowledge Engineering

Inference Engine
The inference engine controls the reasoning involved when the system is run. It has its own mechanism for interpreting the stored knowledge (in the appropriate form), and for sequencing the steps involved in reaching conclusions. Inference here means any of the methods by which the system reaches conclusions.

Inference Engine
Facts All animals breathe oxygen.
All dogs are animals.

Infer

All dogs breathe oxygen.

Inference Mechanisms

GOAL
Forward chaining fact driven bottom - up Backward chaining goal driven top- down

Facts
The selection of the inference paradigm strongly influences the overall performance of the ES

Explanation System
If the user is to have confidence in the output from an ES, it will be important for the ES to have ways of explaining how its conclusions were arrived at. It will be useful to allow the user to ask In response to a question from the ES:

WHY (did you ask that question)?

After a conclusion has been presented:

HOW (did you reach that conclusion)?

Blackboard
This just means a place where temporary working may be stored, where it is accessible to various component parts of a large ES. This may include, for example, a (dynamic) agenda --- a list of tasks to be done (by the ES). It may also include a list of intermediate conclusions, or results of searches, in order to avoid duplication of effort. Not all ES will use (or need) a blackboard.

Knowledge Refinement Subsystem

Knowledge refinement means analyzing experience and adjusting the body of stored knowledge as a result. People do this all the time, and a good ES can do it too. This may consist merely of saving previous results for future reference, to avoid repeating searches or computations. OR it may involve feedback from the user, e.g. You (the ES) gave me this advice and it was BAD/GOOD

ES Development Tools
Conventional Programming Symbolic Programming ES Shells

Expert Systems
ES's are: 1. Open to inspection, both in presenting intermediate steps and in answering questions about the solution process. 2. Easily modified, both in adding and deleting skills from the knowledge base. 3. Heuristic, in using knowledge to obtain solutions Development of Expert Systems will allow us not only to provide very powerful technical capabilities but also to further nurture our own understanding of human thought process.

An ideal ES should include:

Extensive specific knowledge from the domain of interest. Extensive database interfaces Application of several techniques. Support for heuristic analysis. Capacity to infer new knowledge from existing knowledge. Decisions under uncertainty Decisions with unknowns Symbolic processing. An ability to explain its own reasoning.

Advantages over human experts

Always and instantly available and performs the same level of expertise. Has direct and instantaneous access to the necessary databases and is not bound to the limited, biased and imperfect recollections of the human. It is logical, objective and consistent. It doesnt forget or make mathematical errors. It multiplies the expertise of the firm by being accessible to the other divisions. It is a repository for the storage of the knowledge of those experts from whose input it was developed.

Benefits of expert systems

Scarce expertise made available. Integration of expertise from different sources. Improved quality (e.g. where an ES assists in design). Ability to work with incomplete information. Reduced system downtime (ES monitors or finds faults). Training (users gain expertise from the ES). Makes expertise available in remote locations. ES can work faster than people. Reliability (ES will not get tired or bored).

Limitations of expert systems compared to human experts:

A human expert is aware of the cultural factors. Human experts are generally aware of the scope and limitations of their knowledge. When faced with a new situation a human expert may develop a new and brilliant approach to solving the problem. People wish to communicate with other people. Human experts are more flexible.

Problems with expert systems

Expert systems are difficult and expensive to develop and maintain. Like all software, ES may contain errors. But unlike other software systems, ES may be designed to cope with incomplete or inconsistent information. If an ES gives a wrong conclusion, it may be difficult to know whether this was caused by an error in the system or by an error in the information given to it.

Problems with expert systems

ES are designed to be used by nonexperts. As above, they are designed not to fail, so errors may show only in wrong conclusions, and a user without expertise may not be in a position to recognize a wrong conclusion.

What Problems Can Expert Systems Solve?

Where to use expert systems?

It is important to match expert systems technology with problems of appropriate scope and complexity. Both end of the spectrum should be avoided. Expert systems that solve trivial problems are a waste of time and money, expert systems that provide simplistic answers to complicated problems are also wasteful.

Survey of Problem -Solving Approaches

Control Design Diagnosis Instruction Interpretation Monitoring Planning Prediction Prescription Selection Simulation

10

20

30%

Expert Systems Personnel and Their Roles

Expert System Consultation

Example: SELECT AUTO Select Auto is an imaginary (rule-based) expert system designed to assist a user to make a right decision when buying a new car. It asks questions about the users need and preferences, and makes recommendations of suitable choices of model. Query:
The desired car is made in
1. 2. 3. United States A foreign country Dont know

Response by user (say): 2

Evaluation of Expert Systems- The Turing Test

Wall

In the Turing test a human communicates with an unseen respondent through a terminal, not knowing if the respondent is a person or a machine. If the tester mistakes computer answers for human answers, the computer successfully passes the Turning test.

ELIZA
Developed by MIT 1966 Called ELIZA after Shaws play - it could be taught to speak increasing well It picked up words from its conversational partner Transform this into a canned response ELIZAs opening statement (appears on the terminal screen): Do you have any problems? Human: Yes. I am unhappy. (types response on the terminal screen) ELIZA: Why are you unhappy? Human: My friend is mean to me. ELIZA: Tell me about your friend. (Rogerian Psychoanalyst) It could fool people into thinking it was a real person but it contained no intelligence.

Components of an Expert System

Expert System Knowledge Base User Interface Inference Engine User

Components of an Expert System

The knowledge base is the collection of facts and rules which describe all the knowledge about the problem domain The inference engine is the part of the system that chooses which facts and rules to apply when trying to solve the users query The user interface is the part of the system which takes in the users query in a readable form and passes it to the inference engine. It then displays the results to the user.

Desirable Features of an Expert System

Dealing with Uncertainty
certainty factors

Explanation Ease of Modification Transportability Adaptive learning

Advantages
Capture of scarce expertise Superior problem solving Reliability Work with incomplete information Transfer of knowledge

Limitations
Expertise hard to extract from experts
dont know how dont want to tell all do it differently

Knowledge not always readily available Difficult to independently validate expertise

Limitations (cont)
High development costs Only work well in narrow domains Can not learn from experience Not all problems are suitable

Expert Systems
An expert system is a computer program that is designed to hold the accumulated knowledge of one or more domain experts

Applications of Expert Systems

PUFF: Medical system for diagnosis of respiratory conditions

PROSPECTOR: Used by geologists to identify sites for drilling or mining

Applications of Expert Systems

MYCIN: Medical system for diagnosing blood disorders. First used in 1979

DESIGN ADVISOR: Gives advice to designers of processor chips

Applications of Expert Systems

DENDRAL: Used to identify the structure of chemical compounds. First used in 1965

LITHIAN: Gives advice to archaeologists examining stone

Components of an Expert System

The knowledge base is the collection of facts and rules which describe all the knowledge about the problem domain The inference engine is the part of the system that chooses which facts and rules to apply when trying to solve the users query The user interface is the part of the system which takes in the users query in a readable form and passes it to the inference engine. It then displays the results to the user.

Why use Expert Systems?

Experts are not always available. An expert system can be used anywhere, any time. Human experts are not 100% reliable or consistent Experts may not be good at explaining decisions Cost effective

Group Decision Support System

Group Decision Support System (GDSS) Contains most of the elements of DSS plus software to provide effective support in group decision-making settings Decision making is shared process Meeting among groups of managers from different areas.

Group Decision Support System

GDSS is an interactive computer- based system that facilitates solution of semi structured and unstructured problems when made by a group of decision makers by concentrating on the process and procedures during meeting.

Group Decision Support System Basic objective

GDSS is to support the process of arriving at a decision.

Group Decision Support System

Two type of GDSS:A same room group whose members are in one locations. virtual group( team) at different location.

Organizational Group Decision Support System

Three levels of decision support: Individual Group Organization

Organizational Group Decision Support System

It support primarily to Planners Analysts Researchers Some managers

Databases

Model base

GDSS processor

GDSS software

Access to the internet and corporate intranet, networks, and other computer system

Dialogue manager

External database access

External databases

Users

Characteristics of a GDSS (1)

Special design Ease of use Flexibility Decision-making support
Delphi approach (decision makers are geographically dispersed) Brainstorming Group consensus Nominal group technique

Characteristics of a GDSS (2)

Anonymous input Reduction of negative group behavior Parallel communication Automated record keeping Cost, control, complexity factors

Group Results Matrix

Components of a GDSS and GDSS Software

Database Model base Dialogue manager Communication capability Special software (also called GroupWare) E.g., Lotus Notes
people located around the world work on the same project, documents, and files, efficiently and at the same time

GDSS Alternatives
high Decision frequency Local area decision network Wide area decision network

Decision room low close

Teleconferencing

distant

Location of group members

Decision Room
Decision Room
For decision makers located in the same geographic area or building Use of computing devices, special software, networking capabilities, display equipment, and a session leader Collect, coordinate, and feed back organized information to help a group make a decision Combines face-to-face verbal interaction with technology-aided formalization

Wide Area Decision Network

Characteristics
Location of group members is distant Decision frequency is high Virtual workgroups
Groups of workers located around the world working on common problems via a GDSS

Executive information system (EIS)

It a computer-based system that serves the information needs of top executives. It provide rapid access to timely and relevant information. Monitoring an organizations performance by directly accessing management reports Improve managerial growth and learning

Executive Support System

Characteristics
A specialized DSS that includes all the hardware, software, data, procedures, and people used to assist senior-level executives within the organization
Board of directors

President

Function area vice presidents

Function area managers

Characteristics of ESS
Tailored to individual executives Easy to use Drill down capabilities Support the need for external data Help with situations with high degree of uncertainty Intelligence support Futures orientation (predictions, forecasting) Linked with value-added business processes

Capabilities of an ESS
Support for
defining overall vision strategic planning strategic organizing and staffing strategic control crisis management

Intelligent support system

It is describes various commercial application such as AI ( artificial intelligence) AI concerned with two basic ideas. It involves studying the thought processes of humans. It deals with representing those processes via machines( computer , robots)

AI techniques
Expert system (ES) Natural language processing (NLP) Speech understanding Robotic and sensory systems Computer vision and scene recognition Machine learning Handwriting recognition Neural computing networks Fuzzy logic Intelligent agents Semantic Web Genetic programming

Benefits of AI
They can make computer easier to use Knowledge more widely available Increases speed Consistency of some problem-solving procedures. Increases the productivity of performing many tasks Rule based systems are the key to automated decision making.

Expert system
Knowledge-based expert systems or simply expert systems Use human knowledge to solve problems that normally would require human intelligence Embody some non-algorithmic expertise Represent the expertise knowledge as data or rules within the computer
Can be called upon when needed to solve problems

EXAMPLES
Diagnostic applications, servicing: People Machinery Play chess Make financial planning decisions Configure computers Monitor real time systems Underwrite insurance policies Perform many other services which previously required human expertise