FORECASTING TECHNIQUES

Dr. V. Sugumaran
Lecture - 07

1
 LEARNING OBJECTIVES

You should be able to:

• Explain the role of demand forecasting & Identify
the components of a forecast
• Compare & contrast qualitative & quantitative
forecasting techniques
• Assess the accuracy of forecasts
• Able to use forecasting techniques for
practical applications

2
 Demand Forecasting

 A forecast is an estimate of future demand &

provides the basis for planning decisions
 The goal is to minimize forecast error
 The factors that influence demand must be
considered when forecasting.
 Managing demand requires timely & accurate
forecasts
 Good forecasting provides reduced inventories,
costs, & stock outs, improved production plans &
customer service
 NEED FOR FORECASTING

• Determines volume of production and production rate

• Forms basis for production, labour and material budgets
• Suggest the need for plant expansion
• Emphasize need for product research development
• Suggest need for changes in production methods
• Establish pricing policies
• Decide extent of advertising and product distribution

4
FACTORS AFFECTING FORECAST
• Business cycle
• Random variation
• Customer’s plan
• Product’s life cycle
• Customers confidence and attitude
• Quality
• Credit policy
• Design of goods or services
• Advertising

5
SOURCES OF DATA

• Data for forecasting is very much vital

• Before designing a model of forecast – relevant
data should be collected
• Data obtained from company records,
published records, journals, surveys,
Government publications, newspapers
• Must consider larger past time period for
collecting data - for the forecasting to be more
reliable

6
Types of Demand Forecasting

• Short term forecasting

 Refers to a period of one year or less – when the demand for
its products is changing very frequently.

• Long term forecasting

 Refers to the forecasts prepared for long period exceeding a
year / 3-4 years /a decade / more than 10 years – during
which, the firms scale of production capacity may be
expanded/reduced.

7
Purpose of short term forecasting
1. Appropriate production schedule - avoid the problem of over
production & under production - every firm has to produce goods
according to a pre-estimated production plan.
2. Reducing cost of purchasing raw-materials and controlling
inventory
3. Determining appropriate price policy - Fix the price as per the
market condition.
4. To evolve a proper advertising policy
It is only through accurate demand estimation
Effective and economical advertisement can be planned by a firm.
5. To forecast short term financial requirements
Financial requirement depends on sales level & volume of production.
If the demand is likely to go up in the near future – financial facilities
are also increases and vice-versa.

8
Purpose of long term forecasting
1. Planning of a new unit or expansion of an existing unit
If the demand is likely to go up in next 10-15 years, expansion of
the existing units or setting up of new units is necessary.
2. To plan for man-power requirement
Training and personnel developments are long term programmes
– long time requirement.
3. To plan for long term financial requirements
Big investments projects require a large amount of finance –
infrastructure development
Before understanding such projects it becomes necessary to
assess the long term demand conditions.

9
Forecasting Techniques

 Qualitative forecasting is based on opinion &

intuition.

 Quantitative forecasting uses mathematical

models & historical data to make forecasts.

 Time series models are the most frequently used

among all the forecasting models.
11
Qualitative methods

1. Opinion survey

2. Executive opinion method

3. Customer and distributor surveys

4. Marketing

5. Market research

6. Delphi technique

12
Opinion survey

• Simple and practicable method for new

products
• Opinions collected from prospective buyers
regarding, why they buy a particular product
and what they expect from that product
• Sampling technique used to survey customers
• Possible to forecast how the targeted
population responds to the product

13
Executive opinion method

• Experts opinion sought on future demand for

the product
• Biased and subjective due to lack of data
• Accuracy depends on skill, expertise and
experience of the person

14
Customer and distributor surveys

• Individuals who have bought a product can be

asked the reasons for making the purchase
• Many companies heavily rely on judgments
made by their sales personnel

15
Marketing

• If the product is entirely new to the customer or

market, difficult to know acceptability of the
product
• Advisable to expose the product to limited
market trial like a controlled experiment in which
the market area and the method of presentation
are carefully selected and controlled
• Cost high – recommended for consumables like
cosmetics, tooth paste etc

16
Market research

• Work assigned to external marketing agencies

• Purpose of research to gather information
regarding the nature of consumption
• Details about various factors which influence
demand like location, buyer occupation, prices,
quantity, quality, consumer income etc., are
collected for forecasting

17
 Delphi technique
• Variant of opinion poll and survey method
• Panel of experts are asked sequential questions in which
the response to one questionnaire is used to produce the
next questionnaire
• Information available to some experts are made available
to the other experts, thus having access to all the
information needed for forecasting
• An iterative process in which opinions are collected from
experts to arrive at a reliable consensus
• Heterogeneous group of experts with different
background are repeatedly questioned for their opinion /
comments on some issues, their agreements &
disagreements are clearly identified.
18
Quantitative Methods

 Time series forecasting – based on the assumption

that the future is an extension of the past. Historical
data is used to predict future demand

 Cause & Effect forecasting – assumes that one or

more factors (independent variables) predict future
demand

It is generally recommended to use a combination of

quantitative & qualitative techniques
 Forecasting Techniques (Continued)

Components of Time Series

Data should be plotted to detect for the following components –

 Trend variations: increasing or decreasing

 Cyclical variations: wavelike movements that are
longer than a year (e.g., business cycle)
 Seasonal variations: show peaks & valleys that
repeat over a consistent interval such as hours,
days, weeks, months, seasons, or years
 Random variations: due to unexpected or
unpredictable events
 Forecasting Techniques (Continued)

Time Series Forecasting Models

Naïve Forecast – the estimate of the next period is

equal to the demand in the past period.

Ft+1 = At

Where Ft+1 = forecast for period t+1

At = actual demand for period t
 Forecasting Techniques (Continued)

Time Series Forecasting Models

Simple Moving Average Forecast – uses historical data

to generate a forecast. Works well when demand is
stable over time.

Where Ft+1 = forecast for period t+1

At = actual demand for period t
n = number of periods to calculate
moving average
 Forecasting Techniques (Continued)

Simple Moving Average

(Fig. 5.1)
 Forecasting Techniques (Continued)

Time Series Forecasting Models

Weighted Moving Average Forecast – is based

on an n-period weighted moving average

Where Ft+1 = forecast for period t+1

Ai = actual demand for period i
n = number of periods to calculate
moving average
wi = weight assigned to period i (Σwi = 1)
 Forecasting Techniques (Continued)

Weighted Moving Average

 Forecasting Techniques (Continued)

Time Series Forecasting Models

Exponential Smoothing Forecast – a type of weighted

moving average where only two data points are needed

Ft+1 = Ft+(At - Ft) or Ft+1 = At + (1 – ) Ft

Where Ft+1 = forecast for Period t + 1

Ft = forecast for Period t
At = actual demand for Period t
 = smoothing constant (0 ≤  ≤1)
 Forecasting Techniques (Continued)

Exponential Smoothing
 Forecast Accuracy

The formula for forecast error, defined as the difference

between actual quantity & the forecast –

Forecast error, et = At - Ft

Where et = forecast error for Period t

At = actual demand for Period t
Ft = forecast for Period t
 Forecast Accuracy (Continued)

Several measures of forecasting accuracy follow –

 Mean absolute deviation (MAD)- a MAD of 0
indicates the forecast exactly predicted demand
 Mean absolute percentage error (MAPE)- provides
a perspective of the true magnitude of the forecast
error
 Mean squared error (MSE)- analogous to variance,
large forecast errors are heavily penalized
 Forecast Accuracy (Continued)

Mean absolute deviation (MAD)-

MAD of 0 indicates the forecast exactly predicted
demand.

Where et = forecast error for period t

At = actual demand for period t
n = number of periods of evaluation
 Forecast Accuracy (Continued)

Mean absolute percentage error (MAPE) –

provides a perspective of the true magnitude of the
forecast error.

Where et = forecast error for period t

At = actual demand for period t
n = number of periods of evaluation
 Forecast Accuracy (Continued)

Mean squared error (MSE) –

analogous to variance, large forecast errors are
heavily penalized

Where et = forecast error for period t

n = number of periods of evaluation
 Forecast Accuracy (Continued)

Running Sum of Forecast Errors (RSFE) –

indicates bias in the forecasts or the tendency of a
forecast to be consistently higher or lower than
actual demand.
n
Running Sum of Forecast Errors, RSFE = e
t 1
t

Where et = forecast error for period t

RSFE
MAD

Forecast Accuracy (Continued)

Tracking signal –
determines if forecast is within acceptable control
limits. If the tracking signal falls outside the pre-set
control limits, there is a bias problem with the
forecasting method and an evaluation of the way
forecasts are generated is warranted.

RSFE
Tracking Signal =
MAD
 Useful Forecasting Websites

 Institute for Forecasting Education

www.forecastingeducation.com
 International Institute of Forecasters
www.forecasters.org
 Forecasting Principles
www.forecastingprinciples.com
 Stata (Data analysis & statistical software)
www.stata.com/links/stat_software.html