3-1 Forecasting 3-2 Forecasting

CHAPTER FORECAST:
3 • A statement about the future value of a variable of
interest such as demand.
• Forecasts affect decisions and activities throughout an
organization
• Accounting, finance
Forecasting • Human resources
• Marketing
• MIS
• Operations
• Product / service design

Operations Management, Eighth Edition, by William J. Stevenson

McGraw-Hill/Irwin Copyright © 2005 by The McGraw-Hill Companies, Inc. All rights reserved.

3-3 Forecasting 3-4 Forecasting

Uses of Forecasts
• Assumes causal system
past ==> future
Accounting Cost/profit estimates • Forecasts rarely perfect because of randomness
Finance Cash flow and funding • Forecasts more accurate for
groups vs. individuals
Human Resources Hiring/recruiting/training • Forecast accuracy decreases
as time horizon increases
Marketing Pricing, promotion, strategy
I see that you will
MIS IT/IS systems, services get an A this semester.

Operations Schedules, MRP, workloads

Product/service design New products and services

3-5 Forecasting 3-6 Forecasting

Elements of a Good Forecast Steps in the Forecasting Process

Timely
“The forecast”

Reliable Accurate
Step 6 Monitor the forecast
Step 5 Prepare the forecast
Step 4 Gather and analyze data
Written Step 3 Select a forecasting technique
Step 2 Establish a time horizon
Step 1 Determine purpose of forecast

3-7 Forecasting 3-8 Forecasting

Types of Forecasts Judgmental Forecasts

• Judgmental - uses subjective inputs • Executive opinions

• Time series - uses historical data assuming the future will be • Sales force opinions
like the past • Consumer surveys
• Associative models - uses explanatory variables to predict the • Outside opinion
future • Delphi method
• Opinions of managers and staff
• Achieves a consensus forecast
3-9 Forecasting 3-10 Forecasting

Time Series Forecasts Forecast Variations

Figure 3.1
• Trend - long-term movement in data
• Seasonality - short-term regular variations in data Irregular
• Cycle – wavelike variations of more than one year’s duration variatio
n
• Irregular variations - caused by unusual circumstances
• Random variations - caused by chance
Trend

Cycles

90
89
88
Seasonal variations

3-11 Forecasting 3-12 Forecasting

Naive Forecasts Naïve Forecasts

• Simple to use
Uh, give me a minute.... • Virtually no cost
We sold 250 wheels last • Quick and easy to prepare
• Data analysis is nonexistent
week.... Now, next week • Easily understandable
we should sell.... • Cannot provide high accuracy
• Can be a standard for accuracy

The forecast for any period equals

the previous period’s actual value.
3-13 Forecasting 3-14 Forecasting

Techniques for Averaging Moving Averages

• Moving average • Moving average – A technique that averages a

• Weighted moving average number of recent actual values, updated as new
• Exponential smoothing values become available.
n

 Ai
MAn = i=1

n
• Weighted moving average – More recent values in a
series are given more weight in computing the
forecast.

3-15 Forecasting 3-16 Forecasting

Simple Moving Average Exponential Smoothing

Ft = Ft-1 + (At-1 - Ft-1)

Actual
MA5
47
45
43
41
• Premise--The most recent observations might have the highest
predictive value.
39
• Therefore, we should give more weight to the more recent time periods when
37 forecasting.
MA3
35
1 2 3 4 5 6 7 8 9 10 11 12
n

 Ai
MAn = i=1

n
 3-17 Forecasting 3-18 Forecasting

Exponential Smoothing Picking a Smoothing Constant

Ft = Ft-1 + (At-1 - Ft-1)

Actual
50
.4
 .1

Dem and
• Weighted averaging method based on previous forecast plus a percentage 45
of the forecast error
• A-F is the error term,  is the % feedback 40

35
1 2 3 4 5 6 7 8 9 10 11 12
Period

3-19 Forecasting 3-20 Forecasting

Linear Trend Equation Calculating a and b

Ft

n  (ty) -  t  y
b =
Ft = a + bt
n t 2 - (  t) 2
• Ft = Forecast for period t
0 1 2 3 4 5 t
• t = Specified number of time periods
• a = Value of Ft at t = 0
• b = Slope of the line
 y - b t
a =
n
3-21 Forecasting 3-22 Forecasting

Linear Trend Equation Example Linear Trend Calculation

t y 5 (2499) - 15(812) 12495-12180

2 b = = = 6.3
Week t Sales ty 5(55) - 225 275 -225
1 1 150 150
2 4 157 314
3 9 162 486
4 16 166 664 812 - 6.3(15)
a = = 143.5
5 25 177 885 5
2
 t = 15 t = 55  y = 812  ty = 2499
2
(t) = 225 y = 143.5 + 6.3t

3-23 Forecasting 3-24 Forecasting

Associative Forecasting Linear Model Seems Reasonable

• Predictor variables - used to predict values of variable interest
X Y Computed
• Regression - technique for fitting a line to a set of points
7 15
• Least squares line - minimizes sum of squared deviations around the line
relationship
2 10
6 13 50

4 15 40

14 25 30

15 27 20

16 24 10

0
12 20 0 5 10 15 20 25

14 27
20 44
15 34
7 17
A straight line is fitted to a set of sample points.
3-25 Forecasting 3-26 Forecasting

Forecast Accuracy MAD, MSE, and MAPE

• Error - difference between actual value and predicted

value  Actual  forecast
MAD =
• Mean Absolute Deviation (MAD) n
• Average absolute error 2
 ( Actual  forecast)
• Mean Squared Error (MSE) MSE =
• Average of squared error n -1
• Mean Absolute Percent Error (MAPE)
• Average absolute percent error ( Actual  forecas / Actual*100)
MAPE =
t
n

3-27 Forecasting 3-28 Forecasting

Controlling the Forecast Sources of Forecast errors

• Control chart • Model may be inadequate

• A visual tool for monitoring forecast errors • Irregular variations
• Used to detect non-randomness in errors
• Incorrect use of forecasting technique
• Forecasting errors are in control if
• All errors are within the control limits
• No patterns, such as trends or cycles, are present
3-29 Forecasting 3-30 Forecasting

Tracking Signal Choosing a Forecasting Technique

• No single technique works in every situation

•Tracking signal
• Two most important factors
• Cost
–Ratio of cumulative error to MAD • Accuracy
• Other factors include the availability of:

Tracking signal =
(Actual-forecast) •
•
Historical data
Computers
MAD • Time needed to gather and analyze the data
• Forecast horizon
Bias – Persistent tendency for forecasts to be
Greater or less than actual values.