FORECASTING

CHAPTER CONTENT

▷Introduction
▷Forecast Accuracy
▷Different Aproaches to Forecasting
▷Qualitative Forecasts
▷Forecast Based on Time-Series Data
▷Associative Forecasting Techniques
▷Choosing a Forecasting Technique
▷Computer Software in Forecasting
 1.
INTRODUCTION
 “
A forecast is an estimate
about the future value of a
variable of interest such as
demand
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 and prices of stocks and bonds.

For the sake of simplicity, this chapter will focus

on the forecasting of demand
Two Important Aspects of
Forecast

▷Expected level of demand

▷Degree of accuracy that can be
assigned to a forecast
Two Uses of Forecast

▷to help managers plan the system

▷to help managers plan the use of the
system
FEATURES COMMON TO ALL
FORECASTS
 General assumption: The same underlying
causal system that existed in the past will
continue to exist in the future

 Forecasts are not perfect

 Forecasts for groups of items tend to be more

accurate than forecasts for individual items

 Forecast accuracy decreases as the time

period covered by the forecast increases
ELEMENTS OF A GOOD FORECAST

 Timeliness: The forecasting time horizon must

cover the time necessary to implement possible
changes

 Accuracy: The degree of accuracy should be

stated to enable users to plan for possible
errors and to provide a basis for comparing
alternative forecasts

 Reliability: The forecasting technique should be

reliable and should work consistently
ELEMENTS OF A GOOD FORECAST

 The forecast should be expressed in

meaningful units

 The forecast should be in writing

 The forecasting technique should be simple to

understand and use

 The forecast should be cost-effective

STEPS IN THE FORECASTING
PROCESS

Step 1: Determine the purpose of the forecast

Step 2: Establish a time horizon
Step 3: Obtain, clean, and analyze appropriate data
Step 4: Select a forecasting technique
Step 5: Make the forecast
Step 6: Monitor the forecast errors
 2.
FORECAST ACCURACY
FORECAST ERROR

Forecast error is the difference between the

value that occurs and the value that was
predicted for a given time period.

Hence, Error = Actual – Forecast

Positive errors result when the forecast is

too low, negative errors result when the
forecast is too high
FORECAST ERROR

Forecast errors influence decisions in two

somewhat different ways.

 In making a choice between various

forecasting alternatives

 In evaluating the success or failure of a

technique in use
FORECAST ACCURACY

Forecast accuracy is based on

the historical error performance
of a forecast
FORECAST ACCURACY

Three commonly used measures for

summarizing historical errors are:

1. The mean absolute deviation (MAD)

2. The mean squared error (MSE)
3. The mean absolute percent error (MAPE)
MAD, MSE & MAPE

 MAD is the  MSE is the  MAPE is the

average average of average
absolute error squared absolute
forecast percent error
 MAD weights errors
all errors  MAPE
evenly  MSE gives weights
more weight relative error
to larger and puts large
errors errors in
perspective
FORMULAE FOR CALCULATING
MAD, MSE AND MAPE
COMPUTE MAD, MSE, and MAPE
for the following data
Actual Sale Forecasted Sale
Period 1 217 215

Period 2 213 216

Period 3 216 215

Period 4 210 214

Period 5 213 211

Period 6 219 214

Period 7 216 217

Period 8 212 216

 3.
DIFFERENT APPROACHES
TO FORECASTING
Qualitative Forecasts Quantitative Forecasts

▷ Consist mainly of ▷ Consist mainly of

subjective inputs objective, inputs

▷ Permits inclusion of ▷ Human factors are often

soft information (e.g., omitted or downplayed
human factors, when quantitative
personal opinions, techniques are used
intuition) in the
forecasting process
▷ Quantitative Forecasting
▷ Qualitative Forecasting techniques: time-series
technique: judgmental forecasts, associative
forecasts models
QUALITATIVE AND QUANTITATIVE
FORECASRING TECHNIQUES
Judgmental forecasts: Forecasts that use subjective
inputs such as opinions from consumer surveys, sales
staff, managers, executives, and experts.

Time-series Forecasts: Forecasts that are based on

patterns identified in recent time-series observations

Associative model: Forecasting technique that uses

explanatory variables to predict future demand.
 4.
QUALITATIVE FORECASTS
QUALITATIVE FORECASTS

There can be many

situations when
forecasters rely solely on
judgment and opinion to
make forecasts
QUALITATIVE FORECASTS

Qualitative forecasts are based on:

1. Executive Opinions
2. Direct-contact composites
3. Consumer Surveys
4. Opinion from other managers, staff
people, and outside experts
5. Delphi Technique
1. Executive Opinions
▷ A small group of upper-level managers (e.g., in marketing,
operations, and finance) meet and collectively develop a
forecast

▷ This approach is often used as a part of long-range

planning and new product development

▷ Advantage: Considerable knowledge and talents of

various managers are brought together

▷ Disadvantage: View of one person may prevail; diffusing

responsibility for the forecast over the entire group may
result in less pressure to produce a good forecast
2. Direct-contact composites

▷ Opinions from the members of the sales staff or the

customer service staff are considered as the basis of
forecast

▷ Advantage: Because of their direct contact with

customers, salesforce are often aware of any plans the
customers may be considering for the future

▷ Disadvantage: Inability to distinguish between what

customers would like to do and what they actually will
do; influence of recent events; conflict of interest
3. Consumer Surveys

▷ Requirements: Considerable amount of knowledge and

skill is required to construct a survey, administer it, and
correctly interpret the results for valid information

▷ Advantage: These surveys can tap information that

might not be available elsewhere

▷ Disadvantage: Surveys can be expensive and time-

consuming; possibility of irrational customer behavior
patterns in reality; low response rates to mail surveys
4. Opinions from other managers and
staff people and outside experts

▷ 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
5. Delphi Technique
▷ A repetitive process in which managers and staff or
outside experts complete a series of questionnaires,
each developed from the previous one, to achieve a
consensus forecast.

▷ For the most part, these are long-term, single-time

forecasts, which usually have very little hard information
to go by or data that are costly to obtain, so the
problem does not lend itself to analytical techniques.
Rather, judgments of experts or others who possess
sufficient knowledge to make predictions are used

▷ Useful for technological forecasting

 5.
FORECASTS BASED ON
TIME-SERIES DATA
 “
A time series is a time-ordered
sequence of observations taken at
regular intervals (e.g., hourly, daily,
weekly, monthly, quarterly, annually)
FORECASTS BASED ON
TIME-SERIES DATA

▷ Forecasting techniques based on time-series

data are made on the assumption that future
values of the series can be estimated from past
values

▷ No attempt is made to identify variables that

influence the series
FORECASTS BASED ON
TIME-SERIES DATA
Analysis of time-series data requires the analyst to identify
the underlying behavior of the series. These behaviors can
be described as:

▷ Trend: A long-term upward or downward movement in

data
▷ Seasonality: Short-term regular variations related to
the calendar or time of day
▷ Cycle: Wavelike variations lasting more than one year
▷ Irregular Variation: Caused by unusual circumstances,
not reflective of typical behavior
▷ Random Variation: Residual variations after all other
behaviors are accounted for
FORECASTING TECCHNIQUES
BASED ON TIME-SERIES DATA

▷ Naive Method
▷ Averaging
▷ Trend Analysis
NAIVE METHOD
A forecast for any period that equals the
previous period’s actual value

▷ Can be used with a stable series

(variations around an average), with
seasonal variations, or with trend

▷ 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
PRACTICE!
PAGE 84-85
NAIVE METHOD

ADVANTAGES DISADVANTAGES

 Inability to provide
 It has no cost highly accurate
forecasts
 It is quick and easy
to prepare

 It is easily
understandable
AVERAGING

Averaging techniques smooth

fluctuations in a time series
because the individual highs and
lows in the data offset each other
when they are combined into an
average.
AVERAGING

Three techniques for averaging:

1. Moving average
2. Weighted moving average
3. Exponential smoothing
MOVING AVERAGE METHOD

A technique that averages a

number of recent actual values,
updated as new values become
available.
FORMULA FOR CALCULATING
MOVING AVERAGE
MOVING AVERAGE METHOD

In a moving average, as each new actual

value becomes available, the forecast is
updated by adding the newest value and
dropping the oldest and then re-computing
the average.

Consequently, the forecast “moves” by

reflecting only the most recent values.
PRACTICE!
PAGE 86-87
MOVING AVERAGE METHOD

ADVANTAGES DISADVANTAGES

 Easy to compute  All values in the

average are
 Easy to understand weighted equally.
WEIGHTED MOVING
AVERAGE METHOD

A weighted moving average is similar to a

moving average, except that it typically
assigns more weight to the most recent
values in a time series

Note: the weights must sum to 1.00

Note: the heaviest weights are assigned to
the most recent values
 FORMULA FOR CALCULATING
WEIGHTED MOVING AVERAGE

The choice of weights Is somewhat arbitrary and generally

involves the use of trial and error to find a suitable
weighting scheme
PRACTICE!
PAGE 88-89
EXPONENTIAL SMOOTHING
METHOD

A weighted averaging method

based on previous forecast plus a
percentage of the forecast error
FORMULA FOR CALCULATING
EXPONENTIAL SMOOTHING
EXPONENTIAL SMOOTHING
METHOD
The smoothing constant α represents a
percentage of the forecast error.

Selecting a smoothing constant is basically a

matter of judgment or trial and error, using
forecast errors to guide the decision.

Commonly used values of α range from .05

to .50.
PRACTICE!
PAGE 89
EXPONENTIAL SMOOTHING
METHOD

▷ Exponential smoothing should begin

several periods back to enable forecasts to
adjust to the data, instead of starting one
period back.
exercise!
PAGE 90-91
 FORECASTING 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
LINEAR TREND
SOME COMMONLY ENCOUNTERED
NON-LINEAR TRENDS
FORECASTING FOR TREND

A simple plot of the data often can

reveal the existence and nature of a
trend.

Note: Our class focuses exclusively on

linear trends based on linear trend
equation because these are fairly common.
TREND ANALYSIS USING
LINEAR TREND EQUATION
Linear Trend Equation:
TREND ANALYSIS USING
LINEAR TREND EQUATION
Equations for Calculating a & b:
exercise!
PAGE 93

Cell phone sales for a California-based firm over the

last 10 weeks are shown in the following table. Plot the
data, and visually check to see if a linear trend line
would be appropriate. Then determine the equation of
the trend line, and predict sales for weeks 11 and 12.
Week Unit Sales Week Unit Sales

1 700 6 742
2 724 7 758
3 720 8 750
4 728 9 770
5 740 10 775
SOLUTION TO THE EXERCISE
Step 1: Data Plotting and Figuring
whether a Trend Line is Appropriate

From the plotted

data, it is visible
that a trend line
would be
appropriate
SOLUTION TO THE EXERCISE
Step 2: Finding the Equation of the Trend Line
SOLUTION TO THE EXERCISE
Step 3: Predicting Sales for Week 11 and 12

Substituting values of t into this equation,

the forecasts for the next two periods
(i.e., t = 11 and t =12) are:

F11 = 699.40 + 7.51(11) = 782.01

F12 = 699.40 + 7.51(12) = 789.52

SOLUTION TO THE EXERCISE
Step 4: Displaying original data, the trend line, and
the two projections (forecasts) on the same graph
PRACTICE!
EXERCISE 7, PAGE 126
 6.
ASSOCIATIVE
FORECASTING
TECHNIQUES
ASSOCIATIVE FORECASTING
TECHNIQUES

Associative techniques rely on identification

of related variables that can be used to
predict values of the variable of interest.

For example, real estate prices are usually

related to property location and square
footage
ASSOCIATIVE FORECASTING
TECHNIQUES
The essence of associative techniques is the
development of an equation that summarizes
the effects of predictor variables (variables that
can be used to predict values of the variable of
interest).

The primary method of analysis is known as

regression, a technique for fitting a line to
a set of points.
SIMPLE LINEAR
REGRESSION
▷ It is the simplest and most widely used form of
regression

▷ It involves a linear relationship between two

variables

▷ The object in linear regression is to obtain an

equation of a straight line that minimizes the sum of
squared vertical deviations of data points from the
line (i.e., the least squares criterion)
SIMPLE LINEAR
REGRESSION
▷ This
▷ least squares line has the
 equation:

where
= Predicted (dependent) variable
x = Predictor (independent) variable
b = Slope of the line
a = Value of when x = 0 (i.e., the
height of the line at the y intercept)

Note: It is conventional to represent values

of the predicted variable on the y axis and
values of the predictor variable on the x
axis.
SIMPLE LINEAR
REGRESSION
Equations for coefficients a and b:
exercise!
PAGE 102

Unit Sales, x Profits, y Unit Sales, x Profits, y

(in $ millions) (in $ millions) (in $ millions) (in $ millions)
7 0.15 16 0.24
2 0.10 12 0.20
6 0.13 14 0.27
4 0.15 20 0.44
14 0.25 15 0.34
15 0.27 7 0.17
SOLUTION CLUES FOR THE
EXERCISE
Step 1: Data plotting and figuring Note: The value of x = 0 is
whether a linear model is reasonable outside the range of observed
values.
Step 2: Using the given formula
obtain the regression equation The regression line should be
used only for the range of
Step 3: Calculate estimated profit values from which it was
when x= $10 million from the developed; the relationship may
regression equation be nonlinear outside that range.

The purpose of the a value is

simply to establish the height of
the line where it crosses the y
Solve it by yourselves! axis
SIMPLE LINEAR REGRESSION

One application of regression in forecasting relates to the use of

indicators (uncontrollable variables that tend to lead or precede
changes in a variable of interest).

Three conditions are required for an indicator to be valid:

1. The relationship between movements of an indicator and

movements of the variable should have a logical explanation.

2. Movements of the indicator must precede movements of the

dependent variable by enough time so that the forecast isn’t
outdated before it can be acted upon.

3. A fairly high correlation should exist between the two variables.

CORRELATION
Correlation is a measure of the strength and direction of
relationship between two variables.

Range: Correlation can range from -1.00 to +1.00

 A correlation of +1.00 indicates that changes in one

variable are always matched by changes in the other

 A correlation of -1.00 indicates that increases in one

variable are matched by decreases in the other

 A correlation close to zero indicates little linear

relationship between two variables.
CORRELATION

The correlation between two

variables can be computed using the
equation:
CORRELATION

▷  square of the correlation coefficient, , provides a measure

The
of the percentage of variability in the values of y that is
“explained” by the independent variable.

Range: The possible values of range from 0 to 1.00

 A high value of (.80 or more), would indicate that the

independent variable is a good predictor of values of the
dependent variable

 A low value (.25 or less) would indicate a poor predictor

 A value between .25 and .80 would indicate a moderate

predictor
WHEN TO USE SIMPLE LINEAR
REGRESSION?
Use of simple regression analysis implies that certain assumptions
have been satisfied.

1. Variations around the line are random. If they are random, no

patterns such as cycles or trends should be apparent when the line
and data are plotted.

2. Deviations around the average value (i.e., the line) should be

normally distributed. A concentration of values close to the line with
a small proportion of larger deviations supports the assumption of
normality.

3. Predictions are being made only within the range of observed

values.
exercise!
PAGE 105
SOLUTION CLUES FOR THE
EXERCISE

Step 1: Data plotting and figuring whether a

linear model is reasonable

Step 2: Using the given formula check the

correlation coefficient “r” to confirm that it is not
close to zero

Step 3: Find out the regression equation

Solve it by yourselves!
 7.
CHOOSING A FORECASTING
TECHNIQUE
CONSIDERATIONS IN CHOOSING A
FORECASTING TECHNIQUE

 Forecasting cost and accuracy

 The availability of historical data
 The availability of computer software
 The time needed to gather and analyze data
and to prepare the
SELECTING AN APPROPRIATE
FORECASTING METHOD
Amount of
Forecasting Historical Data Pattern Forecast Preparation Personnel
Method Horizon Time Background
Data

Moving 2 to 30 Variation Little

around Short Short
average observations an average sophistication

Simple Variation
5 to 10 Little
exponential observations around Short Short sophistication
smoothing an average

Trend models 10 to 20 Trend Short to Short Moderate

observations medium sophistication

10 Long
Causal observations Can handle Short, development Considerable
regression per complex medium, time, short time
sophistication
models independent patterns or long for
variable implementation
 8.
COMPUTER SOFTWARE IN
FORECASTING
Computers play an important role in preparing forecasts
based on quantitative data.

Their use allows managers to develop and revise

forecasts quickly, and without the burden of manual
computations.

Microsoft Excel is the most frequently used and readily

available software for this purpose.
Thanks!
Any questions?