MODULE 4 – DEMAND FORECASTING 1

MODULE 4 – DEMAND FORECASTING

INTRODUCTION

A forecast is a prediction of future events used for planning purposes. Planning, on the
other hand, is the process of making management decisions on how to deploy resources to best
respond to the demand forecasts. Forecasting methods may be based on mathematical models
that use available historical data, or on qualitative methods that draw on managerial experience
and judgments, or on a combination of both.

Forecasts are useful for both managing processes and managing supply chains. At the
supply chain level, a firm needs forecasts to coordinate with its customers and suppliers. At the
process level, output forecasts are needed to design the various processes throughout the
organization, including identifying and dealing with in-house bottlenecks.

In this module, our focus is on demand forecasts. We begin with different types of demand
patterns. We examine forecasting methods in three basic categories: (1) judgment, (2) causal,
and (3) time-series methods. Forecast errors are defined, providing important clues for making
better forecasts. We next consider the forecasting techniques themselves, and then how they can
be combined to bring together insights from several sources.

LEARNING OUTCOMES:

After reading this module, the learner should be able to:

1. Identify the five basic patterns of most demand time series.
2. Identify the various measures of forecast errors.
3. Use regression to make forecasts with one or more independent variables.
4. Make forecasts using the most common approaches for time-series analysis.
5. Make forecasts with seasonality.
6. Describe a typical forecasting process used by businesses

TIME:

The time allotted for this module is three hours.

LEARNER DESCRIPTION

The participants in this module are 3rd Year BSA students.

MGT6 – OPERATIONS MANAGEMENT AND TQM

 MODULE 4 – DEMAND FORECASTING 2

MODULE CONTENTS:

The organization-wide forecasting process cuts across functional areas. Forecasting

overall demand typically originates with marketing, but internal customers throughout the
organization depend on forecasts to formulate and execute their plans as well. Forecasts are
critical inputs to business plans, annual plans, and budgets..

LESSON 4.1: Overview of Forecasting

Forecast is a statement about the future

• It assumes a causal system i.e. future resembles the past
• They are rarely perfect because of randomness
• They are more accurate for groups vs. individuals (Forecasting errors among items in a
group usually have a canceling effect)
• Forecast accuracy decreases as time horizon for forecasts increases

Elements of a Good Forecast:

• Timely
• Reliable
• Accurate
• Meaningful
• Written
• Easy to Use

Steps in the Forecasting Process

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

Demand Patterns
Forecasting demand in some situations requires uncovering the underlying patterns from
available information. The repeated observations of demand for a service or product in their order
of occurrence form a pattern known as a time series. There are five basic patterns of most demand
time series:
1. Horizontal. The fluctuation of data around a constant mean.
2. Trend. The systematic increase or decrease in the mean of the series over time.
3. Seasonal. A repeatable pattern of increases or decreases in demand, depending on the
time of day, week, month, or season.
4. Cyclical. The less predictable gradual increases or decreases in demand over longer
periods of time (years or decades).
5. Random. The unforecastable variation in demand.

MGT6 – OPERATIONS MANAGEMENT AND TQM

 MODULE 4 – DEMAND FORECASTING 3

Figure 1. Demand Patterns (Krajewski, Ritzman, and Malhotra 2016)

Key Decisions on Making Forecasts

Before using forecasting techniques, a manager must make two decisions:
1. Deciding What to Forecast - Although some sort of demand estimate is needed for the
individual services or goods produced by a company, forecasting total demand for groups
or clusters and then deriving individual service or product forecasts may be easiest. Also,
selecting the correct unit of measurement (e.g., service or product units or machine-hours)
for forecasting may be as important as choosing the best method.
2. Choosing the Type of Forecasting Technique - The forecaster’s objective is to develop
a useful forecast from the information at hand with the technique that is appropriate for
the different patterns of demand. Two general types of forecasting techniques are used:
judgment methods and quantitative methods.
• Judgmental - Subjective analysis of subjective inputs
• Causal Methods – Analyzes historical data to reveal relationships between (easily or
in advance) observable quantities and forecast quantities. Uses this relationship to
make predictions.
• Time series – Objective analysis historical data assuming the future will be like the
past

MGT6 – OPERATIONS MANAGEMENT AND TQM

 MODULE 4 – DEMAND FORECASTING 4

LESSON 4.2: Forecasting Techniques / Methods

Forecasting systems offer a variety of techniques, and no one of them is best for all items
and situations. The forecaster’s objective is to develop a useful forecast from the information at
hand with the technique that is appropriate for the different patterns of demand.

Judgmental Forecasting
Forecasts from quantitative methods are possible only when there is adequate historical
data, (i.e., the history file). However, the history file may be nonexistent when a new product is
introduced or when technology is expected to change. In some cases, judgment methods are the
only practical way to make a forecast. In other cases, judgment methods can also be used to
modify forecasts that are generated by quantitative methods. Four of the more successful
judgment methods are as follows:
1. Salesforce estimates are forecasts compiled from estimates made periodically by
members of a company’s salesforce. The salesforce is the group most likely to know which
services or products customers will be buying in the near future and in what quantities.
2. Executive opinion is a forecasting method in which the opinions, experience, and
technical knowledge of one or more managers or customers are summarized to arrive at
a single forecast. All of the factors going into judgmental forecasts would fall into the
category of executive opinion. Executive opinion can also be used for technological
forecasting.
3. Market research is a systematic approach to determine external consumer interest in a
service or product by creating and testing hypotheses through data-gathering surveys.
Although market research yields important information, it typically includes numerous
qualifications and hedges in the findings.
4. The Delphi method is a process of gaining consensus from a group of experts while
maintaining their anonymity. This form of forecasting is useful when no historical data are
available from which to develop statistical models and when managers inside the firm have
no experience on which to base informed projections

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 (e.g., government actions or
advertising promotions) can be identified. These relationships are expressed in mathematical
terms and can be complex.
In linear regression, one variable, called a dependent variable, is related to one or more
independent variables by a linear equation. The dependent variable (such as demand for door
hinges) is the one the manager wants to forecast. The independent variables (such as advertising
expenditures and new housing starts) are assumed to affect the dependent variable and thereby
“cause” the results observed in the past.
In the simplest linear regression models, the dependent variable is a function of only one
independent variable and, therefore, the theoretical relationship is a straight line: Y = a + bX,
where, Y = dependent variable; X = independent variable; a = Y-intercept of the line; and b =
slope of the line

MGT6 – OPERATIONS MANAGEMENT AND TQM

 MODULE 4 – DEMAND FORECASTING 5

The sample correlation coefficient, r, measures the direction and strength of the
relationship between the independent variable and the dependent variable. A correlation
coefficient of +1.00 implies that period-by-period changes in direction (increases or decreases) of
the independent variable are always accompanied by changes in the same direction by the
dependent variable. An r of -1.00 means that decreases in the independent variable are always
accompanied by increases in the dependent variable, and vice versa. A zero value of r means no
linear relationship exists between the variables. The closer the value of r is to { 1.00, the better
the regression line fits the points.
The sample coefficient of determination measures the amount of variation in the
dependent variable about its mean that is explained by the regression line. The coefficient of
determination is the square of the correlation coefficient, or R-squared. The value of R-squared
ranges from 0.00 to 1.00. Regression equations with a value of R-squared close to 1.00 mean a
close fit.

Figure 2. Regression Analysis Chart (Krajewski, Ritzman, and Malhotra 2016)

Time-Series Methods
These methods are based on the assumption that the dependent variable’s past pattern
will continue in the future. Time-series analysis identifies the underlying patterns of demand that
combine to produce an observed historical pattern of the dependent variable and then develops
a model to replicate it.

Method #1: Naïve Forecasting

A method often used in practice is the naïve forecast, whereby the forecast for the next
period (Ft+1) equals the demand for the current period (Dt). So if the actual demand for

MGT6 – OPERATIONS MANAGEMENT AND TQM

 MODULE 4 – DEMAND FORECASTING 6

Wednesday is 35 customers, the forecasted demand for Thursday is 35 customers. Despite its
name, the naïve forecast can perform well.
The naïve forecast method also may be used to account for seasonal patterns. If the
demand last July was 50,000 units, and assuming no underlying trend from one year to the next,
the forecast for this July would be 50,000 units.

Method #2: Simple Moving Average

The simple moving average method simply involves calculating the average demand for
the n most recent time periods and using it as the forecast for future time periods. For the next
period, after the demand is known, the oldest demand from the previous average is replaced with
the most recent demand and the average is recalculated. In this way, the n most recent demands
are used, and the average “moves” from period to period.
Specifically, the forecast for period t + 1 can be calculated at the end of period t (after the
actual demand for period t is known) as

Method #3: Weighted Moving Average

In the simple moving average method, each demand has the same weight in the
average—namely, 1/n. In the weighted moving average method, each historical demand in the
average can have its own weight. The sum of the weights equals 1.0. For example, in a three-
period weighted moving average model, the most recent period might be assigned a weight of
0.50, the second most recent might be weighted 0.30, and the third most recent might be weighted
0.20. The average is obtained by multiplying the weight of each period by the value for that period
and adding the products together.
The advantage of a weighted moving average method is that it allows you to emphasize
recent demand over earlier demand. (It can even handle seasonal effects by putting higher
weights on prior years in the same season.) The forecast will be more responsive to changes in
the underlying average of the demand series than the simple moving average forecast.

Method #4: Exponential Smoothing

The exponential smoothing method is a sophisticated weighted moving average method
that calculates the average of a time series by implicitly giving recent demands more weight than
earlier demands, all the way back to the first period in the history file. It is the most frequently
used formal forecasting method because of its simplicity and the small amount of data needed to
support it. Unlike the weighted moving average method, which requires n periods of past demand
and n weights, exponential smoothing requires only three items of data: (1) the last period’s
forecast; (2) the actual demand for this period; and (3) a smoothing parameter, alpha (a), which

MGT6 – OPERATIONS MANAGEMENT AND TQM

 MODULE 4 – DEMAND FORECASTING 7

has a value between 0 and 1.0. The equation for the exponentially smoothed forecast for period
t + 1 is calculated

The emphasis given to the most recent demand levels can be adjusted by changing the
smoothing parameter. Larger alpha values emphasize recent levels of demand and result in
forecasts more responsive to changes in the underlying average. Smaller alpha values treat past
demand more uniformly and result in more stable forecasts.

Method #5: Seasonal Patterns

Seasonal patterns are regularly repeating upward or downward movements in demand
measured in periods of less than one year (hours, days, weeks, months, or quarters). In this
context, the time periods are called seasons.
The multiplicative seasonal method uses an estimate of average demand which is
multiplied by seasonal factors to arrive at a seasonal forecast. The four-step procedure presented
here involves the use of simple averages of past demand, although more sophisticated methods
for calculating averages, such as a moving average or exponential smoothing approach, could be
used. The following description is based on a seasonal pattern lasting one year and seasons of
one month, although the procedure can be used for any seasonal pattern and season of any
length:
1. For each year, calculate the average demand per season by dividing annual demand by
the number of seasons per year.
2. For each year, divide the actual demand for a season by the average demand per season.
The result is a seasonal index for each season in the year, which indicates the level of
demand relative to the average demand. For example, a seasonal index of 1.14 calculated
for April implies that April’s demand is 14 percent greater than the average demand per
month.
3. Calculate the average seasonal index for each season, using the results from step 2. Add
the seasonal indices for a season and divide by the number of years of data.
4. Calculate each season’s forecast for next year. Begin by forecasting next year’s annual
demand using the naïve method, moving averages, exponential smoothing, or trend
projection with regression. Then, divide annual demand by the number of seasons per
year to get the average demand per season. Finally, make the seasonal forecast by
multiplying the average demand per season by the appropriate seasonal index found in
step 3.

LESSON 4.3: Choosing a Quantitative Forecasting Method

Forecast Accuracy
Forecast error measures provide important information for choosing the best forecasting
method for a service or product. They also guide managers in selecting the best values for the

MGT6 – OPERATIONS MANAGEMENT AND TQM

 MODULE 4 – DEMAND FORECASTING 8

parameters needed for the method: n for the moving average method, the weights for the
weighted moving average method, alpha for the exponential smoothing method, and when
regression data begins for the trend projection with regression method. The criteria to use in
making forecast method and parameter choices include (1) minimizing bias (CFE); (2) minimizing
MAPE, MAD, or MSE; (3) maximizing R-squared ; (4) meeting managerial expectations of
changes in the components of demand; and (5) minimizing the forecast errors in recent periods.

Forecast error for a given period t is simply the difference found by subtracting the forecast
from actual demand, or

The cumulative sum of forecast errors (CFE) measures the total forecast error. CFE is
also called the bias error and results from consistent mistakes—the forecast is always too high or
too low. This type of error typically causes the greatest disruption to planning efforts.

The average forecast error, sometimes called the mean bias, is simply

The mean squared error (MSE), standard deviation of the errors (s), and mean absolute
deviation (MAD) measure the dispersion of forecast errors attributed to trend, seasonal, cyclical,
or random effects:

If MSE, sigma, or MAD is small, the forecast is typically close to actual demand; by
contrast, a large value indicates the possibility of large forecast errors. The measures do differ in
the way they emphasize errors. Large errors get far more weight in MSE and sigma because the
errors are squared. MAD is a widely used measure of forecast error and is easily understood; it

MGT6 – OPERATIONS MANAGEMENT AND TQM

 MODULE 4 – DEMAND FORECASTING 9

is merely the mean of the absolute forecast errors over a series of time periods, without regard to
whether the error was an overestimate or an underestimate.
The mean absolute percent error (MAPE) relates the forecast error to the level of demand
and is useful for putting forecast performance in the proper perspective:

Principles for the Forecasting Process

1. Better processes yield better forecasts.
2. Demand forecasting is being done in virtually every company, either formally or informally.
The challenge is to do it well—better than the competition.
3. Better forecasts result in better customer service and lower costs, as well as better
relationships with suppliers and customers.
4. The forecast can and must make sense based on the big picture, economic outlook,
market share, and so on.
5. The best way to improve forecast accuracy is to focus on reducing forecast error
6. Bias is the worst kind of forecast error; strive for zero bias.
7. Whenever possible, forecast at more aggregate levels. Forecast in detail only where
necessary.
8. Far more can be gained by people collaborating and communicating well than by using
the most advanced forecasting technique or model.

ONLINE READING MATERIALS:

 Read the article by Prevedere about “3 Real World Market Demand Forecasting
Success Stories” at https://www.prevedere.com/3-real-world-market-demand-
forecasting-stories/
 Read the article by Chris Fry about “6 Trends Reshaping Business Forecasting” at
https://resources.businesstalentgroup.com/btg-blog/6-trends-business-forecasting

ONLINE VIDEO LINKS AND MATERIALS:

 Watch the online video lecture of the course instructor uploaded at NEO LMS and to the
class shared Google drive (if applicable).
 Watch a Youtube Videos by Joshua Emmanuel about the “Forecasting” at
o https://www.youtube.com/watch?v=Wo5YWXDRXv8&list=PLD3fYc0bAjC8fZJFa
GGG0sCQeiVqI6EJI&index=2&t=0s
o https://www.youtube.com/watch?v=C5J_QSR7ST0&list=PLD3fYc0bAjC8fZJFaG
GG0sCQeiVqI6EJI&index=5&t=0s
o https://www.youtube.com/watch?v=k_HN0wOKDd0&list=PLD3fYc0bAjC8fZJFaG
GG0sCQeiVqI6EJI&index=4&t=0s

MGT6 – OPERATIONS MANAGEMENT AND TQM

 MODULE 4 – DEMAND FORECASTING 10

o https://www.youtube.com/watch?v=DipOB2H6ick&list=PLD3fYc0bAjC8fZJFaGG
G0sCQeiVqI6EJI&index=3&t=0s

TEST YOUR KNOWLEDGE:

MODULE REFERENCES:

Stevenson, William (2018), Project Management; the managerial process 7th ed.
Stevenson, William (2018), Operations Management 13th Edition
Zani, Rosliza (2018), Operation management
Krajewski, Lee J. (2016) Operation management: sustainability and supply chain management
12th ed.
Verma, A.P. (2016). Industrial Engineering and Management

MGT6 – OPERATIONS MANAGEMENT AND TQM