Professional Documents
Culture Documents
Chapter 13
How Forecasting
fits the Operations Management
Philosophy
Operations As a Competitive
Weapon
Operations Strategy
Project Management
Process Strategy
Process Analysis
Process Performance and Quality
Constraint Management
Process Layout
Lean Systems
Forecasting at Unilever
Customer demand planning (CDP), which is critical
to managing value chains, begins with accurate
forecasts.
Unilever has a state-of-the-art CDP system that
blends historical shipment data with promotional
data and current order data.
Statistical forecasts are adjusted with planned
promotion predictions.
Forecasts are frequently reviewed and adjusted with
point of sale data.
This has enabled Unilever to reduce its inventory
and improved its customer service.
2007 Pearson Education
Demand Patterns
Demand Patterns
Horizontal
Trend
Seasonal
Cyclical
Designing the
Forecast System
Deciding what to forecast
Level of aggregation.
Units of measure.
Quantitative methods
Causal
Time-series
2007 Pearson Education
Deciding
What To Forecast
Few companies err by more than 5 percent when
forecasting total demand for all their services or
products. Errors in forecasts for individual items
may be much higher.
Level of Aggregation: The act of clustering several
similar services or products so that companies can
obtain more accurate forecasts.
Units of measurement: Forecasts of sales revenue
are not helpful because prices fluctuate.
Forecast the number of units of demand then translate
into sales revenue estimates
Stock-keeping unit (SKU): An individual item or product
that has an identifying code and is held in inventory
somewhere along the value chain.
2007 Pearson Education
Short Term
Medium Term
Long Term
(03 months)
(3 months 2 years)
Forecast
Quality
Individual
products or
services
Total sales
Groups or families
of products or
services
Total sales
Decision
Area
Inventory
management
Final assembly
scheduling
Workforce
scheduling
Master production
scheduling
Staff planning
Production
planning
Master production
scheduling
Purchasing
Distribution
Facility location
Capacity planning
Process
management
Causal
Judgment
Causal
Judgment
Judgment Methods
Sales force estimates: The forecasts that are compiled from
estimates of future demands made periodically by members of
a companys sales force.
Executive opinion: A forecasting method in which the
opinions, experience, and technical knowledge of one or more
managers are summarized to arrive at a single forecast.
Executive opinion can also be used for technological
forecasting to keep abreast of the latest advances in
technology.
Market research: A systematic approach to determine
external consumer interest in a service or product by creating
and testing hypotheses through data-gathering surveys.
Delphi method: A process of gaining consensus from a group
of experts while maintaining their anonymity.
2007 Pearson Education
Causal Methods
Linear Regression
Causal methods are used when historical data are
available and the relationship between the factor to
be forecasted and other external or internal factors
can be identified.
Linear regression: A causal method in which one
variable (the dependent variable) is related to one or
more independent variables by a linear equation.
Dependent variable: The variable that one wants to
forecast.
Independent variables: Variables that are assumed
to affect the dependent variable and thereby cause
the results observed in the past.
2007 Pearson Education
Causal Methods
Linear Regression
Dependent variable
Deviation,
Estimate of or error
Y from
regression
equation
Regression
equation:
Y = a + bX
Y = dependent variable
X = independent variable
a = Y-intercept of the line
b = slope of the line
Actual
value
of Y
Value of X used
to estimate Y
X
Independent variable
2007 Pearson Education
Linear Regression
Example 13.1
The following are sales and advertising data for the past 5 months for
brass door hinges. The marketing manager says that next month the
company will spend $1,750 on advertising for the product. Use linear
regression to develop an equation and a forecast for this product.
Month
Sales
(000 units)
Advertising
(000 $)
1
2
3
4
5
264
116
165
101
209
2.5
1.3
1.4
1.0
2.0
a =
b =
r =
r2 =
syx=
8.135
109.229X
0.98
0.96
15.603
Y = a + bX
250
200
Y = 8.135 + 109.229X
150
100
50
a =
b =
r =
r2 =
syx=
8.135
109.229X
0.98
0.96
15.603
|
|
|
|
1.0
1.5
2.0
2.5
Advertising (thousands of dollars)
Forecasting Error
For any forecasting method, it is important to
measure the accuracy of its forecasts.
Forecast error is the difference found by
subtracting the forecast from actual demand
for a given period.
Et = Dt - Ft
where
Et = forecast error for period t
Dt = actual demand for period t
2007 Pearson Education
Patient
Arrivals
1
2
3
400
380
411
Example 13.2
Solution
450
Patient arrivals
430
410
390
370
Actual patient
arrivals
0
2007 Pearson Education
|
5
|
10
|
15
Week
|
20
|
25
|
30
Example 13.2
Solution continued
a.
Week
1
2
3
4
5
Arrivals Average
400
380
411
397
415
402
?
b.
c.
Forecast for week 5
is the average of
the arrivals for
weeks 2,3 and 4
Comparison of
3- and 6-Week MA Forecasts
Patient Arrivals
3-week moving
average forecast
Week
2007 Pearson Education
6-week moving
average forecast
Application 13.1
We will use the following customer-arrival
data in this moving average application:
F5
780
3
3
F6
801.667
3
3
2007 Pearson
2007 Pearson
Exponential Smoothing
Exponential smoothing method: A sophisticated
weighted moving average method that calculates
the average of a time series by giving recent
demands more weight than earlier demands.
Ft+1 = (Demand this period) + (1 )(Forecast calculated last period)
= Dt + (1 )Ft
Or an equivalent equation:
Ft+1 = Ft + (Dt Ft )
Where alpha (is a smoothing parameter with a value between 0 and 1.0
Exponential smoothing is the most frequently used formal forecasting
method because of its simplicity and the small amount of data needed
to support it.
2007 Pearson Education
Exponential Smoothing
Example 13.3
Reconsider the medical clinic patient
arrival data. It is now the end of week 3.
a. Using = 0.10, calculate the
exponential smoothing forecast for
week 4.
Ft+1 = Dt + (1-)Ft
F4 = 0.10(411) + 0.90(390) = 392.1
Week
1
2
3
4
5
Arrivals
400
380
411
415
?
Trend-Adjusted
Exponential Smoothing
A trend in a time series is a systematic increase or
decrease in the average of the series over time.
Where a significant trend is present, exponential smoothing
approaches must be modified; otherwise, the forecasts tend
to be below or above the actual demand.
Trend-Adjusted Exponential
Smoothing Formula
Ft+1 = At +Tt
where At = Dt + (1 )(At-1 + Tt-1)
Tt = (At At-1) + (1 )Tt-1
At = exponentially smoothed average of the series in period t
Tt = exponentially smoothed average of the trend in period t
= smoothing parameter for the average
= smoothing parameter for the trend
Dt = demand for period t
Ft+1 = forecast for period t + 1
2007 Pearson Education
Trend-Adjusted
Exponential Smoothing
Example 13.4 Medanalysis ran an average of 28
blood tests per week during the past four weeks. The trend
over that period was 3 additional patients per week. This
weeks demand was for 27 blood tests. We use = 0.20 and
= 0.20 to calculate the forecast for next week.
A0 = 28 patients and Tt = 3 patients
At = Dt + (1 )(At-1 + Tt-1)
A1= 0.20(27) + 0.80(28 + 3) = 30.2
Tt = (At At-1) + (1 )Tt-1
T1 = 0.20(30.2 2.8) + 0.80(3) = 2.8
Ft+1 = At + Tt
F2 = 30.2 + 2.8 = 33 blood tests
2007 Pearson Education
70
Patient arrivals
60
50
Actual blood
test requests
40
30
|
1
|
2
|
3
|
4
|
5
|
6
|
|
7 8
Week
|
9
|
|
|
|
10 11 12 13
|
|
14 15
Application 13.2
The forecaster for Canine Gourmet dog breath
fresheners estimated (in March) the sales
average to be 300,000 cases sold per month
and the trend to be +8,000 per month.
The actual sales for April were 330,000 cases.
What is the forecast for May,
assuming = 0.20 and = 0.10?
thousand
thousand
To make forecasts for periods beyond the next period, multiply the trend
estimate by the number of additional periods, and add the result to the
current
average
2007
Pearson Education
2007 Pearson
Seasonal Patterns
Seasonal patterns are regularly repeated upward
or downward movements in demand measured in
periods of less than one year.
An easy way to account for seasonal effects is to use one
of the techniques already described but to limit the data in
the time series to those time periods in the same season.
Multiplicative Seasonal
Method
Step 1: For each year, calculate the average
demand for each season by dividing annual
demand by the number of seasons per year.
Step 2: For each year, divide the actual demand for
each season by the average demand per season,
resulting in a seasonal index for each season of the
year, indicating the level of demand relative to the
average demand.
Step 3: Calculate the average seasonal index for
each season using the results from Step 2. Add the
seasonal indices for each season and divide by the
number of years of data.
Step 4: Calculate each seasons forecast for next
year.
2007 Pearson Education
Year 1
Year 2
Year 3
Year 4
45
335
520
100
70
370
590
170
100
585
830
285
100
725
1160
215
1000
1200
1800
2200
Demand has been increasing by an average of 400 customers each year. The forecast
demand is found by extending that trend, and projecting an annual demand in year 5 of 2,200
+ 400 = 2,600 customers.
Comparison of
Seasonal Patterns
Multiplicative pattern
Additive pattern
Measures of
Forecast Error
Cumulative sum of forecast errors (CFE): A
measurement of the total forecast error that
assesses the bias in a forecast. CFE = Et
Mean squared error (MSE): A measurement of the
dispersion of forecast errors.
Et2
MSE =
n
Mean absolute deviation (MAD): A measurement
of the dispersion of forecast errors.
MAD = |Et |
n
Standard deviation (): A measurement
(Et E )2
of the dispersion of forecast errors. =
2007 Pearson Education
n1
Measures of
Forecast Error
Mean absolute percent error (MAPE): A
measurement that relates the forecast error to the
level of demand and is useful for putting forecast
performance in the proper perspective.
MAPE =
[ |Et | / Dt ](100)
n
Demand,
Dt
Forecast,
Ft
1
2
3
4
5
6
7
8
200
240
300
270
230
260
210
275
225
220
285
290
250
240
250
240
Total
Error,
Et
Absolute
Error
Absolute
Percent
Squared, Error,
Error,
E t2
|Et|
(|Et|/Dt)(100)
-25
20
15
20
20
20
40
35
625
400
225
400
400
400
1600
1225
25
20
15
20
20
20
40
35
12.5%
8.3
5.0
7.4
8.7
7.7
19.0
12.7
15
5275
195
81.3%
CFE = 15
= 27.4
195
MAD =
= 24.4
8
15
= 1.875
8
5275
MSE =
= 659.4
8
Tracking signal =
E=
CFE
=
MAD
81.3%
MAPE =
= 10.2%
8
-15
= -0.6148
24.4
Equivalent
Number of
Percentage of Area
within Control Limits
1.0
1.5
2.0
2.5
3.0
3.5
4.0
0.80
1.20
1.60
2.00
2.40
2.80
3.20
57.62
76.98
89.04
95.44
98.36
99.48
99.86
Computer Support
Computer support, such as OM Explorer, makes error calculations
easy when evaluating how well forecasting models fit with past data.
+2.0
Out of control
Control limit
Tracking signal
+1.5
+1.0
+0.5
0
0.5
CFE
Tracking signal =
MAD
1.0
Control limit
1.5
0
2007 Pearson Education
|
5
|
|
|
10
15
20
Observation number
|
25
Results Sheet
Moving Average
Results Sheet
Weighted Moving Average
Results Sheet
Exponential Smoothing
Results Sheet
Trend-Adjusted
Exponential Smoothing
Forecasting as a Process
The forecast process itself, typically done on a
monthly basis, consists of structured steps. They
often are facilitated by someone who might be called
a demand manager, forecast analyst, or
demand/supply planner.
Denver Air-Quality
Discussion Question 1
250
225
Year 2
Visibility rating
200
175
150
125
100
75
50
Year 1
25
0
|
22
|
25
|
28
July
2007 Pearson Education
|
31
|
3
|
6
|
9
Date
|
12
|
15
|
|
18 21
August
|
14
|
27
|
30