Documenti di Didattica
Documenti di Professioni
Documenti di Cultura
Chapter Eighteen
McGraw-Hill/Irwin Copyright 2014 by The McGraw-Hill Companies, Inc. All rights reserved.
182
Copyright 2014 by McGraw Hill Education (India) Private Limited. All rights reserved.
LO181: Understand how forecasting is
essential to supply chain planning
184
Copyright 2014 by McGraw Hill Education (India) Private Limited. All rights reserved.
There are four basic types of forecasts.
Qualitative
Time series analysis (primary focus of this
chapter)
Causal relationships
Simulation
186
Copyright 2014 by McGraw Hill Education (India) Private Limited. All rights reserved.
Average
demand for a Trend
period of time
Seasonal Cyclical
element elements
Random
Autocorrelation
variation
187
Demand for product or service
1
Year
Seasonal peaks
2
Year
Random
variation
3
Year
over four years
Average demand
4
Year
line
Trend component
Actual demand
Copyright 2014 by McGraw Hill Education (India) Private Limited. All rights reserved.
188
Copyright 2014 by McGraw Hill Education (India) Private Limited. All rights reserved.
Identification of trend lines is a common
starting point when developing a forecast.
Common trend types include linear, S-curve,
asymptotic, and exponential.
189
Copyright 2014 by McGraw Hill Education (India) Private Limited. All rights reserved.
Using the past to predict the future
Short term forecasting less than 3 months
1810
Copyright 2014 by McGraw Hill Education (India) Private Limited. All rights reserved.
Choosing an appropriate forecasting
model depends upon
Time horizon to be forecast
Data availability
Accuracy required
Size of forecasting budget
Availability of qualified personnel
1811
Copyright 2014 by McGraw Hill Education (India) Private Limited. All rights reserved.
Amount of Historical Forecast
Forecasting Method Data Pattern
Data Horizon
6 to 12 months; Stationary (i.e.,
Simple moving
weekly data are often no trend or Short
average
used seasonality)
Weighted moving
average and simple 5 to 10 observations
Stationary Short
exponential needed to start
smoothing
Exponential 5 to 10 observations
Stationary and
smoothing with needed to start Short
trend
trend
Stationary,
Short to
Linear regression 10 to 20 observations trend, and
medium
seasonality
1812
Copyright 2014 by McGraw Hill Education (India) Private Limited. All rights reserved.
Forecast is the average of a fixed number of past
periods.
Copyright 2014 by McGraw Hill Education (India) Private Limited. All rights reserved.
1814
Copyright 2014 by McGraw Hill Education (India) Private Limited. All rights reserved.
The simple moving average formula implies
equal weighting for all periods.
A weighted moving average allows unequal
weighting of prior time periods.
The sum of the weights must be equal to one.
Often, more recent periods are given higher
weights than periods farther in the past.
= +
+ +
1815
Copyright 2014 by McGraw Hill Education (India) Private Limited. All rights reserved.
A weighted average method that includes all
past data in the forecasting calculation
1816
Copyright 2014 by McGraw Hill Education (India) Private Limited. All rights reserved.
Well accepted for six reasons
Exponential models are surprisingly accurate
Formulating an exponential model is relatively
easy
The user can understand how the model works
Little computation is required to use the model
Computer storage requirements are small
Tests for accuracy are easy to compute
1817
18-18
Copyright 2014 by McGraw Hill Education (India) Private Limited. All rights reserved.
1818
Copyright 2014 by McGraw Hill Education (India) Private Limited. All rights reserved.
Regression is used to identify the functional
relationship between two or more correlated variables,
usually from observed data.
One variable (the dependent variable) is predicted for
given values of the other variable (the independent
variable).
Linear regression is a special case that assumes the
relationship between the variables can be explained
with a straight line.
Y = a + bx
1819
Copyright 2014 by McGraw Hill Education (India) Private Limited. All rights reserved.
The least squares method Quarter Sales Quarter Sales
determines the parameters a 1 600 7 2,600
and b such that the sum of the 2 1,550 8 2,900
squared errors is minimized 3 1,500 9 3,800
least squares 4 1,500 10 4,500
5 2,400 11 4,000
6 3,100 12 4,900
1820
Copyright 2014 by McGraw Hill Education (India) Private Limited. All rights reserved.
Forecast error is the difference between the forecast
value and what actually occurred.
All forecasts contain some level of error.
Sources of error
Bias when a consistent mistake is made
Random errors that are not explained by the model
being used
Measures of error
Mean absolute deviation (MAD)
Mean absolute percent error (MAPE)
Tracking signal
1821