Professional Documents
Culture Documents
Chapter Eighteen
McGraw-Hill/Irwin Copyright © 2014 by The McGraw-Hill Companies, Inc. All rights reserved.
18–2
• LO18–1: Understand how forecasting is essential to
supply chain planning
18–4
• Decoupling point: Point at which inventory is
stored, which allows SC to operate independently.
Seasonal Cyclical
element elements
Random
Autocorrelation
variation Excel: Components
of Demand
18–8
• Using the past to predict the future
Short term – forecasting less than 3 months
18–9
• Choosing an appropriate forecasting
model depends upon
– Time horizon to be forecast
– Data availability
– Accuracy required
– Size of forecasting budget
– Availability of qualified personnel
18–10
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,
smoothing with needed to start Seasonality Short
trend Trend
Stationary,
Short to
Linear regression 10 to 20 observations trend, and
medium
seasonality
18–11
• Forecast is the average of a fixed number of past
periods.
18–13
18-14
18–14
• 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.
𝐹𝑡 = 𝑤1𝐴𝑡 − 1 + 𝑤2𝐴𝑡 − 2 + …+
𝑤𝑛𝐴𝑡 − 𝑛
18–15
• Experience and/or trial-and-error are the
simplest approaches.
18–16
• A weighted average method that includes all
past data in the forecasting calculation
18–17
• 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
18–18
18-19
18–19
Week Demand Forecast
1 820 820
2 775 820
3 680 811
4 655 785
5 750 759
6 802 757
7 798 766
8 689 772
9 775 756
10 760
18-20
18–20
• Step 1: Compute the initial estimate of the
mean (or level)n of the series at time period t = 0
yt
0 = y = t =1
n
• Step 2: Compute the updated estimate by using
the smoothing equation
T = yT + (1 − ) T −1
Slide 21
18–21
Note that
T = yT + (1 − ) T −1
= yT + (1 − )[ yT −1 + (1 − ) T −2 ]
= yT + (1 − ) yT −1 + (1 − )2 T −2
Slide 22
18–22
• Point forecast made at time T for yT+p
yˆT + p (T ) = T ( p = 1, 2,3,...)
• SSE, MSE, and the standard errors at time T
T
SSE = [ y t − yˆ t (t − 1)]2
t =1
SSE
MSE = , s = MSE
T −1
Note: There is no theoretical justification for dividing SSE by
(T – number of smoothing constants). However, we use this
divisor because it agrees to the computation of s in Box-Jenkins
models introduced later.
Slide 23
18–23
• The presence of a trend in the data causes the
exponential smoothing forecast to always lag behind
the actual data
• This can be corrected by adding a trend adjustment
– The trend smoothing constant is delta (δ)
18–24
• Calculate the new forecast, assuming the
following:
– The previous forecast including trend (FITt-1) is 110
and the previous estimate of the trend (Tt-1) is 10
– α = 0.2 and δ = 0.3
– Actual demand for period t-1 is 115
18–26
• 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 + bt
18–27
Sales = 10 + 1.2*Adv+ 0.9*Incentives
18–28
• 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
18–29
• Ideally, MAD will be zero (no • MAPE scales the forecast error to
forecasting error). the magnitude of demand.
• Larger values of MAD
indicate a less accurate
model.
18–30
18–31
18–32
• Causal relationship forecasting uses
independent variables other than time to
predict future demand.
– This independent variable must be a leading
indicator.
18–33
• Often, more than one independent
variable may be a valid predictor of
future demand.
18–35
• A web-based process used to coordinate the
efforts of a supply chain.
– Demand forecasting
– Production and purchasing
– Inventory replenishment
• Integrates all members of a supply chain –
manufacturers, distributors, and retailers.
• Depends upon the exchange of internal
information to provide a more reliable view of
demand.
18–36
Creation of a
Development
front-end Joint business Sharing Inventory
of demand
partnership planning forecasts replenishment
forecasts
agreement
18–37
• Forecasting is a fundamental step in any planning
process.