OPERATIONS MANAGEMENT

14e

WILLIAM J. STEVENSON
Rochester Institute of Technology

Irwin/McGraw-Hill ©The McGraw-Hill Companies,

Inc., 1999
 CHAPTER THREE

CHAPTER THREE
FORECASTING

Irwin/McGraw-Hill ©The McGraw-Hill Companies,

Inc., 1999
 Learning Objectives

After completing this chapter, you should be able

to:
•List features common to all forecasts.
•List the elements of a good forecast.
•Outline the steps in the forecasting process.
•Describe four qualitative forecasting techniques.
•Describe the key factors and trade-offs to
consider when choosing a forecasting technique
 3.1. Introduction

• A forecast is an estimate about the future value of a

variable such as demand.
• The better the estimate, the more informed decisions
can be.
• Some forecasts are long range, covering several years
or more.
• Forecasts are a basic input in the decision processes
of operations management because they provide
information on future demand.
• The primary goal of operations management is to
match supply to demand.
 Forecast Uses
• Plan the system
• Generally involves long-range plans related to:
A. Types of products and services to offer
B. Facility and equipment levels
C. Facility location
• Plan the use of the system
• Generally involves short- and medium-range
plans related to:
A. Inventory management
B. Workforce levels
C. Purchasing
D. Budgeting
 Business forecasting pertains to more
than predicting demand.
 Forecasts are also used to predict
profits, revenues, costs, productivity
changes, prices and availability of
energy and raw materials, interest
rates, movements of key economic
indicators (e.g., gross domestic
product, inflation, government
borrowing), and prices of stocks and
bonds.
3.2. Features Common to All Forecasts

A wide variety of forecasting techniques are in use.

In many respects, they are quite different from each other, as
you shall soon discover.
Nonetheless, certain features are common to all, and it is
important to recognize them;
• Forecasts are not perfect: Actual results usually differ from
predicted values; the presence of randomness precludes a
perfect forecast. Allowances should be made for forecast
errors
2. Forecasts for groups of items tend to be more accurate than
forecasts for individual items because forecasting errors
among items in a group usually have a canceling effect.
3. Forecast accuracy decreases as time horizon increases.
 Forecasting Individual
Items (High
Variability)
Suppose the store predicts daily demand for each item:
1) Coca-Cola: 100 bottles (but actual demand is 90 → error = -10)
2) Pepsi: 80 bottles (but actual demand is 95 → error = +15)
3) Sprite: 60 bottles (but actual demand is 65 → error = +5)
4) Fanta: 50 bottles (but actual demand is 45 → error = -5)
Each forecast has an error, which can be positive
(underestimation) or negative (overestimation).
 Forecasting the Total
Group (Lower Error)
The total forecasted demand for all
beverages: 100 + 80 + 60 + 50 = 290
bottles
The actual total demand: 90 + 95 + 65 +
45 = 295 bottles
Total error = 295 - 290 = +5 bottles
(much smaller compared to individual item
errors)
 Why Does This
Happen?

Some errors cancel each other out:

Coca-Cola was overestimated (-10), but
Pepsi was underestimated (+15),
reducing the overall error.
The group forecast is based on overall
trends rather than random
fluctuations in individual items.
 3.3 Elements of a Good Forecast

Timely

it ve
c
ff e
Reliable Accurate t e
o s
C
se
f ul u
ng Written to
ni sy
e a Ea
M
1. Timely: A forecast must be available on time to
be useful for decision-making. Example: A sales
forecast for the upcoming quarter should be ready
before the start of the quarter so that the business
can plan inventory, staffing, and marketing
activities accordingly.
2. Reliable: The forecast must be consistent and
dependable over time. Example: A retailer
expects a predictable sales volume for winter
clothing based on previous years’ data.
3. Accuracy: A forecast should strive for high
accuracy—that is, how close the forecasted value
is to the actual outcome. Example: A manufacturer
forecasts the demand for a product at 10,000 units,
and the actual demand turns out to be 9,800 units.
This is accurate
4. Cost-Effective: The resources spent on
generating a forecast should be
proportional to the benefits it provides.
Example: An organization might spend a
significant amount of money using
sophisticated data models to predict next-
quarter sales.
5. Meaningful: A forecast should be relevant
to the decision-making needs of the business
or individual. Example: A forecast of total
sales by region is more meaningful than a
forecast of sales broken down by individual
store if the company is considering
expansion into a new region.
6. Written: Forecasts should be clearly
documented in writing or through a formal
report. Example: A quarterly sales forecast
should be in a written report, with clearly
defined assumptions, methodologies, and
data sources, so it can be reviewed by
management, finance, and operations teams.
7. Easy to Use: The forecast should be user-
friendly and easily interpreted by decision-
makers, even if they aren’t experts in
forecasting. Example: A sales forecast
presented as a simple graph or table, makes
it easier for managers to interpret and act
upon.
3.4 Steps in the Forecasting Process

“The forecast”

Step 6 Monitor the forecast

Step 5 Make the forecast
Step 4 Gather and analyze data
Step 3 Select a forecasting technique
Step 2 Establish a time horizon
Step 1 Determine purpose of forecast
1. Determine the purpose of the forecast. How
will it be used and when will it be needed?
2. Establish a time horizon. The forecast must
indicate a time interval, keeping in mind that
accuracy decreases as the time horizon increases.
3. Obtain, clean, and analyze appropriate data.
Obtaining the data can involve significant effort.
Once obtained, the data may need to be
“cleaned” to get rid of outliers and obviously
incorrect data before analysis.
4. Monitor the forecast errors. The forecast
errors should be monitored to determine if the
forecast is performing in a satisfactory manner.
 3.5 Approaches to Forecasting
There are two general approaches to forecasting:
qualitative and quantitative.
A.Qualitative Methods consist mainly of subjective
inputs, which often defy precise numerical description.
 Qualitative techniques permit inclusion of soft
information (e.g., human factors, personal opinions,
hunches) in the forecasting process.
B.Quantitative methods involve either the projection
of historical data or the development of associative
models that attempt to utilize causal (explanatory)
(Independent) variables to make a forecast. And mainly
of analyzing objective, or hard, data.
 They usually avoid personal biases that sometimes
contaminate qualitative methods.
• The following pages present a variety of
forecasting techniques that are classified as
judgmental, time-series, or associative.

A.Judgmental - uses subjective inputs

(qualitative)

B.Time series - uses historical data assuming

the future will be like the past (quantitative)

C.Associative models - uses explanatory

variables to predict the future
 3.6 Judgmental Forecasts
(Qualitative)
•E xecutive opinions.
• Opinions of managers and staff

•S ales force.

•C onsumer surveys.

•D elphi method.
1. Executive Opinions
 A small group of upper-level managers (e.g., in
marketing, operations, and finance) may meet
and collectively develop a forecast.
 This approach is often used as a part of long-
range planning and new product development.
 It has the advantage of bringing together the
considerable knowledge and talents of various
managers.
 However, there is the risk that the view of one
person will prevail, and the possibility that
diffusing responsibility for the forecast over the
entire group may result in less pressure to
produce a good forecast
2. Sales force Opinions
• Members of the sales staff or the customer service
staff are often good sources of information because
of their direct contact with consumers.
• They are often aware of any plans the customers
may be considering for the future.
• There are, however, several drawbacks to using
sales force opinions.:
• The staff members may be unable to distinguish between
what customers would like to do and what they actually
will do.
• The people are sometimes overly influenced by recent
experiences.
• In addition, if forecasts are used to establish sales quotas,
there will be a conflict of interest because it is to the
salesperson’s advantage to provide low sales estimates.
3. Consumer Surveys
• The organizations seeking consumer input usually resort to consumer
surveys, which enable them to sample consumer opinions.
I. The obvious advantage of consumer surveys is that they can tap
information that might not be available elsewhere.
II. On the other hand, a considerable amount of knowledge and skill is
required to construct a survey, administer it, and correctly interpret
the results for valid information.
III. Surveys can be expensive and time-consuming.
IV. In addition, even under the best conditions, surveys of the general
public must contend with the possibility of irrational behavior
patterns. Along the same lines, low response rates to a mail survey
should—but often don’t— make the result suspect
I. If these and similar pitfalls can be avoided, surveys can produce useful
information
4. Other Approaches
• A manager may solicit opinions from a number
of other managers and staff people.
• Occasionally, outside experts are needed to help
with a forecast. Advice may be needed on
political or economic conditions in the country
or a foreign country, or some other aspect of
importance with which an organization lacks
familiarity.
• Another approach is the Delphi method, an
iterative process intended to achieve a
consensus forecast.
• This method involves circulating a series of
questionnaires among individuals who possess
the knowledge and ability to contribute
meaningfully.
 Time Series Forecasts
(Quantitative)
A time series is a time-ordered sequence of observations
taken at regular intervals (e.g., hourly, daily, weekly,
monthly, quarterly, annually).
The data may be measurements of demand, sales, earnings,
profits, shipments, accidents, output, precipitation,
productivity, or the consumer price index.
Forecasting techniques based on time-series data are
made on the assumption that future values of the series
can be estimated from past values.
• Analysis of time-series data requires the analyst to identify
the underlying behavior of the series.
• This can often be accomplished by merely plotting the data
and visually examining the plot.
• One or more patterns might appear: trends, seasonal
variations, cycles, or variations around an average
• In addition, there will be random and perhaps irregular
variations. These behaviors can be described as follows:
• Trend refers to a long-term upward or downward movement
in the data.
• Seasonality refers to short-term, fairly regular variations
generally related to factors such as the calendar or time of
day. Restaurants, and supermarkets, weekly and even daily
“seasonal” variations.
3. Cycles are wave like variations of more than one year’s
duration. These are often related to a variety of
economic, political, and even agricultural conditions.
4. Irregular variations are due to unusual circumstances
such as severe weather conditions, strikes, or a major
change in a product or service. Whenever possible, these
should be identified and removed from the data.
5. Random variations are residual variations that remain
after all other behaviors have been accounted for.
Also known as noise, these are minor fluctuations that
occur without any clear reason.
Typically short-lived and do not follow a pattern.
Example: Daily stock price fluctuations.
 Forecast Variations
Figure 3-1

Irregular
variation

Trend

cycle
Cycles

90
89
88
Seasonal variations
 The Forecasting Techniques

1) Naïve
2) Simple Moving
Average
3) Weighted Moving
Average
4) Exponential
Smoothing
5) ES with Trend.
 Naïve Forecast
Naive forecast : A forecast for any period that equals the
previous period’s actual value.
1)Simple to Use: No math or modeling needed
2)Virtually no Cost: No special tools or software
required
3)Data Analysis is Nonexistent: Just use the last actual
value, You don’t analyze trends, seasonality, or
cycles
4)Easily Understandable: Anyone can apply it, Anyone
can grasp how it works.
5)Cannot Provide High Accuracy: Doesn’t account for
trends, seasonality, or changes
 Naive Forecast (Last
Value Method)

• For example,
forecast for July =
Actual for June
• Ft+1 = At
• FJul= AJun= 600
• Forecast Very
Sensitive to
Demand Changes;
Good for stable
demand
 Naive Forecast with
Trend (Difference
Method):
• For data with trend, the forecast is
equal to the last value of the series plus
or minus the difference between the last
two values of the series.
• For example, suppose the last two
values were 50 and 53. The next
forecast would be 56:
 Exercise on Naive
Forecasting
You are given the following monthly sales data for a product over the past six months:

Month Sales
January 200
February 220
March 210
April 230
May 240
June 235

Task:

1. Calculate the naive forecast for July and August.

2. What is the forecast error for July (assuming actual sales in July are 250)?
 Exercise: Naive Forecast
with Trend
You are given the following monthly sales data for a product over the past five months:

Month Sales
January 50
February 60
March 70
April 80
May 90

The data shows an increasing trend in sales.

Task:

1. Calculate the naive forecast for June and July using the Naive Forecast with Trend method.
2. Assume the actual sales for June are 95. What is the forecast error for June?
Techniques for Averaging
1. Moving Average
• One weakness of the naive method is that the
forecast just traces the actual data, with a lag
of one period; it does not smooth at all. But by
expanding the amount of historical data a
forecast is based on, this difficulty can be
overcome.
• A moving average forecast uses a number of
the most recent actual data values in
generating a forecast. The moving average
forecast can be computed using the following
equation:
• For example, MA3 would refer to a three-period
moving average forecast, and MA5 would refer to
a five-period moving average forecast.
• Compute a three-period moving average forecast
given demand for shopping carts for the last five
periods.
Solution
 Points to Know on Moving Averages

• Pro: Easy to compute and understand

• Con: All data points were created equal
2. Weighted Moving Average
• A weighted average is similar to a moving
average, except that it typically assigns more
weight to the most recent values in a time
series.
• For instance, the most recent value might be
assigned a weight of .40, the next most recent
value a weight of .30, the next after that a
weight of .20, and the next after that a weight
of .10.
• Note that the weights must sum to 1.00, and
that the heaviest weights are assigned to the
most recent values.
Example, Computing a Weighted Moving Average
•Given the following demand data,
a.Compute a weighted average forecast using a weight of .40 for the most recent
period, .30 for the next most recent, .20 for the next, and .10 for the next.
b.If the actual demand for period 6 is 39, forecast demand for period 7 using the
same weights as in part a.

Period Demand
1 42
2 40
3 43
Solution 4 40
a. F6 = .10( 40
5 ) + .20( 43 41
) + .30( 40 ) + .40( 41 ) =
41.0
b.F 7 = .10( 43 ) + .20( 40 ) + .30( 41 ) + .40( 39 ) =
40.2
3. Exponential Smoothing
• Exponential smoothing is a sophisticated
weighted averaging method that is still
relatively easy to use and understand.
• Each new forecast is based on the previous
forecast plus a percentage of the difference
between that forecast and the actual value of
the series at that point. That is:
• The smoothing constant α represents a
percentage of the forecast error.
• Each new forecast is equal to the previous
forecast plus a percentage of the previous
error.
• For example, suppose the previous forecast
(F5) was 42 units, actual demand was 40
units, and α = .10. The new (F6) forecast
would be computed as follows:
• F t = 42 + .10(40 − 42 ) = 41.8
• Then, if the actual demand turns out to be 43,
the next forecast would be
• F t = 41.8 + .10(43 − 41.8 ) = 41.92
• An alternate form of Formula 3–3a reveals the
weighting of the previous forecast and the latest
actual demand:
• F t = (1 − α) F t−1 + α A t−1 ......... (3–3b)
• For example, if α = .10, this would be
• F t = .90 F t−1 + .10 A t−1

• The quickness of forecast adjustment to error is

determined by the smoothing constant, α. The closer
its value is to zero, the slower the forecast will be to
adjust to forecast errors (i.e., the greater the
smoothing).
• Conversely, the closer the value of α is to 1.00, the
greater the responsiveness and the less the smoothing
This is illustrated in Figure 3.4B.
 Techniques for Trend
• Analysis of trend involves developing an
equation that will suitably describe trend
(assuming that trend is present in the data).
The trend component may be linear, or it may
not. The discussion here focuses exclusively on
linear trends because these are fairly common.
 Linear Trend Equation Example
t y
Week t2 Sales ty
1 1 150 150
2 4 157 314
3 9 162 486
4 16 166 664
5 25 177 885

 t = 15 t2 = 55  y = 812  ty = 2499

(t)2 = 225
 Linear Trend Calculation

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

b = = = 6.3
5(55) - 225 275 - 225

812 - 6.3(15)
a = = 143.5
5
y = 143.5 + 6.3t
Interpretation: The equation y=143.5+6.3t suggests a
linear trend where sales start at 143.5 units and increase
by 6.3 units each week.
 Disadvantage of simple linear regression

1. Apply only to linear relationship with an

independent variable.
2. One needs a considerable amount of data to
establish the relationship ( at least 20).
3. All observations are weighted equally
 Forecast Accuracy
• Forecast error
difference between forecast and
actual demand
•MAD
• mean absolute deviation
•MAPD
• mean absolute percent deviation
•Cumulative error
•Average error or bias
1. Mean Absolute Deviation (MAD)

 At - Ft 
MAD = n
where
t = period number
At = demand in period t
Ft = forecast for period t
n = total number of periods
= absolute value
 MAD Example
PERIOD DEMAND, At Ft ( =0.3) ( A t - F t) |A t - F t|
1 37 37.00 – –
2 40 37.00 3.00 3.00
3 41 37.90 3.10 3.10
4 37 38.83 -1.83 1.83
5 45 38.28 6.72 6.72
6 50 40.29 9.69 9.69
7 43 43.20 -0.20 0.20
8 47 43.14 3.86 3.86
9 56 44.30 11.70 11.70
10 52 47.81 4.19 4.19
11 55 49.06 5.94 5.94
12 54 50.84 3.15 3.15
557 49.31 53.39
  At - Ft 
MAD = n
53.39
=
11
= 4.85

Interpretation: This means that, on average, the

company's sales forecasts were off by 4.85 units
per week or t period
Other Accuracy Measures

2. Mean absolute percent deviation (MAPD)

|At - Ft|
MAPD =
At
3. Cumulative error
E = et
4. Average error
et
(E )=
n
 Comparison of
Forecasts

FORECAST MAD MAPD E ( E)

Exponential smoothing (= 0.30) 4.85 9.6% 49.31 4.48
Exponential smoothing (= 0.50) 4.04 8.5% 33.21 3.02
(= 0.50, = 0.30)
 Forecast Control
• Tracking signal
• monitors the forecast to see if it is
biased high or low

(At - Ft) E
Tracking signal = =
MAD MAD
 Tracking Signal Values
DEMAND FORECAST, ERROR E = TRACKING
PERIOD At Ft At - Ft (At - Ft) MAD SIGNAL

1 37 37.00 – – – –
2 40 37.00 3.00 3.00 3.00 1.00
3 41 37.90 3.10 6.10 3.05 2.00
4 37 38.83 -1.83 4.27 2.64 1.62
5 45 38.28 6.72 10.99 3.66 3.00
6 50 40.29 9.69 20.68 4.87 4.25
7 43 43.20 -0.20 20.48 4.09 5.01
8 47 43.14 3.86 24.34 4.06 6.00
9 56 44.30 11.70 36.04 5.01 7.19
10 52 47.81 4.19 40.23 4.92 8.18
11 55 49.06 5.94 46.17 5.02 9.20
12 54 50.84 3.15 49.32 4.85 10.17
Tracking signal for period 3

TS3 = 6.10 = 2.00

3.05
 Sources of forecast errors
• The model may be inadequate.
• Irregular variation may be occur.
• The forecasting technique may be used
incorrectly or the results misinterpreted.
• There are always random variation in the data.
 End Notes
• The two most important factors in
choosing a forecasting technique:
• Cost
• Accuracy
• Keep it SIMPLE!
END