FORECASTING

Forecast is a statement about the future value of a variable of interest.

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. Having a forecast of demand is essential for determining how much capacity or supply will
be needed to meet demand.

Two aspects of forecasts are important:

One is the expected level of demand; the other is the degree of accuracy that can be assigned to a
forecast (i.e., the potential size of forecast error).

Forecasts are made with reference to a specific time horizon. The time horizon may be fairly short
(e.g., an hour, day, week, or month), or somewhat longer (e.g., the next six months, the next year,
the next five years, or the life of a product or service).

Short-term forecasts pertain to ongoing operations. Long-range forecasts can be an important

strategic planning tool.

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.

In spite of its use of computers and sophisticated mathematical models, forecasting is not an exact
science. Instead, successful forecasting often requires a skillful blending of science and intuition.
Some forecasting techniques work better than others, but no single technique works all the time.

Forecast accuracy decreases as the time period covered by the forecast—the time horizon—
increases.
Steps in the forecasting process:
1. Determine the purpose of the forecast. How will it be used and when will it be needed?
This step will provide an indication of the level of detail required in the forecast, the amount of
resources (personnel, computer time, dollars) that can be justified, and the level of accuracy
necessary.
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. Select a forecasting technique.
5. Make the forecast.
6. Monitor the forecast. A forecast has to be monitored to determine whether it is performing in a
satisfactory manner. If it is not, re-examine the method, assumptions, validity of data, and so on;
modify as needed; and prepare a revised forecast.
APPROACHES TO FORECASTING
There are two general approaches to forecasting: qualitative and quantitative.
Qualitative methods consist mainly of subjective inputs, which often defy precise numerical
description.
Quantitative methods involve either the projection of historical data or the development of
associative models that attempt to utilize causal (explanatory) variables to make a forecast.

Qualitative techniques permit inclusion of soft information (e.g., human factors, personal opinions,
hunches) in the forecasting process. Those factors are often omitted or downplayed when
quantitative techniques are used because they are difficult or impossible to quantify.
Quantitative techniques consist mainly of analyzing objective, or hard, data. They usually avoid
personal biases that sometimes contaminate qualitative methods.
In practice, either approach or a combination of both approaches might be used to develop a forecast.
QUALITATIVE FORECASTS:
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 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.
However, several drawbacks are there in using sales-force opinions:
• One is that staff members may be unable to distinguish between what customers would like
to do and what they actually will do.
• Another is that these people are sometimes overly influenced by recent experiences. Thus,
after several periods of low sales, their estimates may tend to become pessimistic. After
several periods of good sales, they may tendto be too optimistic.
• 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
Because it is the consumers who ultimately determine demand, it seems natural to solicit input from
them, which enable them to sample consumer opinions.
The obvious advantage of consumer surveys is that they can tap information that might not be
available elsewhere.
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.
A few drawbacks are:
• Surveys can be expensive and time-consuming.
• Even under the best conditions, surveys of the general public must contend with the
possibility of irrational behavior patterns. For example, much of the consumer’s thoughtful
 information gathering before purchasing a new car is often undermined by the glitter of a
new car showroom or a high-pressure sales pitch.
• Low response rates to mail surveys are another hindrance to surveys.
4) Delphi Method:
An iterative process in which managers and staff complete a series of questionnaires,each developed
from the previous one, to achieve a consensus forecast.
Responses are kept anonymous, which tends to encourage honest responses and reduces the risk that
one person’s opinion will prevail.
As a forecasting tool, the Delphi method is useful for technological forecasting, that is, for assessing
changes in technology and their impact on an organization. Often the goal is to predict when a certain
event will occur.

QUANTITATIVE FORECASTING METHODS

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).
The data may be measurements of demand, 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. Although no attempt is made to identify variables that
influence the series, these methods are widely used, often with quite satisfactory results.
Analysis of time-series data requires the analyst to identify the underlying behaviour 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.
1. Trend refers to a long-term upward or downward movement in the data. Population shifts,
changing incomes, and cultural changes often account for such movements.
2. Seasonality refers to short-term, fairly regular variations generally related to factors such as the
calendar or time of day. Restaurants, supermarkets, and theaters experience weekly and even daily
“seasonal” variations.
3. Cycles are wavelike 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. They do not reflect typical behavior, and their inclusion
in the series can distort the overall picture. 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.
TIME SERIES MODELS
Model Description
Naïve Uses last period’s actual value as a forecast

Simple Mean (Average) Uses an average of all past data as a forecast

Uses an average of a specified number of the most

Simple Moving Average recent observations, with each observation receiving the
same emphasis (weight)

Uses an average of a specified number of the most

Weighted Moving Average recent observations, with each observation receiving a
different emphasis (weight)

A weighted average procedure with weights declining

Exponential Smoothing
exponentially as data become older

Technique that uses the least squares method to fit a

Trend Projection
straight line to the data

A mechanism for adjusting the forecast to accommodate

Seasonal Indexes
any seasonal patterns inherent in the data

Analogy method in Forecasting:

It is a judgmental forecasting technique based on identifying a sales history that is analogous to a
present situation, such as the sales history of a similar product, and using that past pattern to predict
future sales.
Quantitative Forecast methods can be further summarized as follows:

1. Opinion Polling Method:

In this method, the opinion of the buyers, sales force and experts could be gathered to determine the
emerging trend in the market.

The opinion polling methods of demand forecasting are of three kinds:

(a) Consumer’s Survey Method or Survey of Buyer’s Intentions:

In this method, the consumers are directly approached to disclose their future purchase plans. I his
is done by interviewing all consumers or a selected group of consumers out of the relevant popu-
lation. This is the direct method of estimating demand in the short run. Here the burden of forecasting
is shifted to the buyer. The firm may go in for complete enumeration or for sample surveys. If the
commodity under consideration is an intermediate product then the industries using it as an end
product are surveyed.

(i) Complete Enumeration Survey:

Under the Complete Enumeration Survey, the firm has to go for a door to door survey for the forecast
period by contacting all the households in the area. This method has an advantage of first hand,
unbiased information, yet it has its share of disadvantages also. The major limitation of this method
is that it requires lot of resources, manpower and time.
In this method, consumers may be reluctant to reveal their purchase plans due to personal privacy
or commercial secrecy. Moreover, at times the consumers may not express their opinion properly or
may deliberately misguide the investigators.

(ii) Sample Survey and Test Marketing:

Under this method some representative households are selected on random basis as samples and
their opinion is taken as the generalised opinion. This method is based on the basic assumption that
the sample truly represents the population. If the sample is the true representative, there is likely to
be no significant difference in the results obtained by the survey. Apart from that, this method is less
tedious and less costly.

A variant of sample survey technique is test marketing. Product testing essentially involves placing
the product with a number of users for a set period. Their reactions to the product are noted after a
period of time and an estimate of likely demand is made from the result. These are suitable for new
products or for radically modified old products for which no prior data exists. It is a more scientific
method of estimating likely demand because it stimulates a national launch in a closely defined
geographical area.

(iii) End Use Method or Input-Output Method:

This method is quite useful for industries which are mainly producer’s goods. In this method, the
sale of the product under consideration is projected as the basis of demand survey of the industries
using this product as an intermediate product, that is, the demand for the final product is the end user
demand of the intermediate product used in the production of this final product.

The end user demand estimation of an intermediate product may involve many final good industries
using this product at home and abroad. It helps us to understand inter-industry’ relations. In input-
output accounting two matrices used are the transaction matrix and the input co-efficient matrix.
The major efforts required by this type are not in its operation but in the collection and presentation
of data.

(b) Sales Force Opinion Method:

This is also known as collective opinion method. In this method, instead of consumers, the opinion
of the salesmen is sought. It is sometimes referred as the “grass roots approach” as it is a bottom-up
method that requires each sales person in the company to make an individual forecast for his or her
particular sales territory.

These individual forecasts are discussed and agreed with the sales manager. The composite of all
forecasts then constitutes the sales forecast for the organisation. The advantages of this method are
that it is easy and cheap. It does not involve any elaborate statistical treatment. The main merit of
this method lies in the collective wisdom of salesmen. This method is more useful in forecasting
sales of new products.

(c) Experts Opinion Method:

This method is also known as “Delphi Technique” of investigation. The Delphi method requires a
panel of experts, who are interrogated through a sequence of questionnaires in which the responses
to one questionnaire are used to produce the next questionnaire. Thus any information available to
some experts and not to others is passed on, enabling all the experts to have access to all the
information for forecasting.
The method is used for long term forecasting to estimate potential sales for new products. This
method presumes two conditions: Firstly, the panellists must be rich in their expertise, possess wide
range of knowledge and experience. Secondly, its conductors are objective in their job. This method
has some exclusive advantages of saving time and other resources.

2. Statistical Method:

Statistical methods have proved to be immensely useful in demand forecasting. In order to maintain
objectivity, that is, by consideration of all implications and viewing the problem from an external
point of view, the statistical methods are used.

The important statistical methods are:

(i) Trend Projection Method:

A firm existing for a long time will have its own data regarding sales for past years. Such data when
arranged chronologically yield what is referred to as ‘time series’. Time series shows the past sales
with effective demand for a particular product under normal conditions. Such data can be given in a
tabular or graphic form for further analysis. This is the most popular method among business firms,
partly because it is simple and inexpensive and partly because time series data often exhibit a
persistent growth trend.

Time series has got four types of components namely, Secular Trend (T), Secular Variation (S),
Cyclical Element (C), and an Irregular or Random Variation (I). These elements are expressed by
the equation O = TSCI. Secular trend refers to the long run changes that occur as a result of general
tendency.

Seasonal variations refer to changes in the short run weather pattern or social habits. Cyclical
variations refer to the changes that occur in industry during depression and boom. Random variation
refers to the factors which are generally able such as wars, strikes, flood, famine and so on.

When a forecast is made the seasonal, cyclical and random variations are removed from the observed
data. Thus only the secular trend is left. This trend is then projected. Trend projection fits a trend
line to a mathematical equation.

The trend can be estimated by using any one of the following methods:

(a) The Graphical Method,

(b) The Least Square Method.

a) Graphical Method:

This is the most simple technique to determine the trend. All values of output or sale for different
years are plotted on a graph and a smooth free hand curve is drawn passing through as many points
as possible. The direction of this free hand curve—upward or downward— shows the trend. A
simple illustration of this method is given in Table 2.

Table 2: Sales of Firm

Sales (Rs.
Year Crore)
1995 40
1996 50
1997 44
1998 60
1999 54
2000 62

In Fig. 1, AB is the trend line which has been drawn as free hand curve passing through the various
points representing actual sale values.

(b) Least Square Method:

Under the least square method, a trend line can be fitted to the time series data with the help of
statistical techniques such as least square regression. When the trend in sales over time is given by
straight line, the equation of this line is of the form: y = a + bx. Where ‘a’ is the intercept and ‘b’
shows the impact of the independent variable. We have two variables—the independent variable x
and the dependent variable y. The line of best fit establishes a kind of mathematical relationship
between the two variables .v and y. This is expressed by the regression у on x.

In order to solve the equation v = a + bx, we have to make use of the following normal
equations:

Σ y = na + b ΣX

Σ xy =a Σ x+b Σ x2

(ii) Barometric Technique:

A barometer is an instrument of measuring change. This method is based on the notion that “the
future can be predicted from certain happenings in the present.” In other words, barometric
techniques are based on the idea that certain events of the present can be used to predict the directions
of change in the future. This is accomplished by the use of economic and statistical indicators which
serve as barometers of economic change.

Generally forecasters correlate a firm’s sales with three series: Leading Series, Coincident or
Concurrent Series and Lagging Series:

(a) The Leading Series:

The leading series comprise those factors which move up or down before the recession or recovery
starts. They tend to reflect future market changes. For example, baby powder sales can be forecasted
by examining the birth rate pattern five years earlier, because there is a correlation between the baby
powder sales and children of five years of age and since baby powder sales today are correlated with
birth rate five years earlier, it is called lagged correlation. Thus we can say that births lead to baby
soaps sales.

(b) Coincident or Concurrent Series:

The coincident or concurrent series are those which move up or down simultaneously with the level
of the economy. They are used in confirming or refuting the validity of the leading indicator used a
few months afterwards. Common examples of coinciding indicators are G.N.P itself, industrial
production, trading and the retail sector.

(c) The Lagging Series:

The lagging series are those which take place after some time lag with respect to the business cycle.
Examples of lagging series are, labour cost per unit of the manufacturing output, loans outstanding,
leading rate of short term loans, etc.

(iii) Regression Analysis:

It attempts to assess the relationship between at least two variables (one or more independent and
one dependent), the purpose being to predict the value of the dependent variable from the specific
value of the independent variable. The basis of this prediction generally is historical data. This
method starts from the assumption that a basic relationship exists between two variables. An
interactive statistical analysis computer package is used to formulate the mathematical relationship
which exists.

For example, one may build up the sales model as:

Quantum of Sales = a. price + b. advertising + c. price of the rival products + d. personal disposable
income +u

Where a, b, c, d are the constants which show the effect of corresponding variables as sales. The
constant u represents the effect of all the variables which have been left out in the equation but
having effect on sales. In the above equation, quantum of sales is the dependent variable and the
variables on the right hand side of the equation are independent variables. If the expected values of
the independent variables are substituted in the equation, the quantum of sales will then be
forecasted.

The regression equation can also be written in a multiplicative form as given below:

Quantum of Sales = (Price)a + (Advertising)b+ (Price of the rival products) c + (Personal disposable
income Y + u

In the above case, the exponent of each variable indicates the elasticities of the corresponding
variable. Stating the independent variables in terms of notation, the equation form is QS = P°8. Ao42 .
R°.83. Y2°.68. 40

Then we can say that 1 per cent increase in price leads to 0.8 per cent change in quantum of sales
and so on.
If we take logarithmic form of the multiple equation, we can write the equation in an additive
form as follows:

log QS = a log P + b log A + с log R + d log Yd + log u

In the above equation, the coefficients a, b, c, and d represent the elasticities of variables P, A, R
and Yd respectively.

The co-efficient in the logarithmic regression equation are very useful in policy decision making by
the management.

(iv) Econometric Models:

Econometric models are an extension of the regression technique whereby a system of independent
regression equation is solved. The requirement for satisfactory use of the econometric model in
forecasting is under three heads: variables, equations and data.

The appropriate procedure in forecasting by econometric methods is model building. Econometrics

attempts to express economic theories in mathematical terms in such a way that they can be verified
by statistical methods and to measure the impact of one economic variable upon another so as to be
able to predict future events.

Utility of Forecasting:

Forecasting reduces the risk associated with business fluctuations which generally produce harmful
effects in business, create unemployment, induce speculation, discourage capital formation and
reduce the profit margin. Forecasting is indispensable and it plays a very important part in the
determination of various policies. In modem times forecasting has been put on scientific footing so
that the risks associated with it have been considerably minimised and the chances of precision
increased.

Forecasts in India:

In most of the advanced countries there are specialised agencies. In India businessmen are not at all
interested in making scientific forecasts. They depend more on chance, luck and astrology. They are
highly superstitious and hence their forecasts are not correct. Sufficient data are not available to
make reliable forescasts. However, statistics alone do not forecast future conditions. Judgment,
experience and knowledge of the particular trade are also necessary to make proper analysis and
interpretation and to arrive at sound conclusions.

Conclusion:

Decision support systems consist of three elements: decision, prediction and control. It is, of course,
with prediction that marketing forecasting is concerned. The forecasting of sales can be regarded as
a system, having inputs apprises and an output.

This simplistic view serves as a useful measure for the analysis of the true worth of sales forecasting
as an aid to management. In spite of all these no one can predict future economic activity with
certainty. Forecasts are estimates about which no one can be sure.

Criteria of a Good Forecasting Method:

There are thus, a good many ways to make a guess about future sales. They show contrast in cost,
flexibility and the adequate skills and sophistication. Therefore, there is a problem of choosing the
best method for a particular demand situation.

There are certain economic criteria of broader applicability. They are:

(i) Accuracy, (ii) Plausibility, (iii) Durability, (iv) Flexibility, (v) Availability, (vi) Economy, (vii)
Simplicity and (viii) Consistency.

(i) Accuracy:

The forecast obtained must be accurate. How is an accurate forecast possible? To obtain an accurate
forecast, it is essential to check the accuracy of past forecasts against present performance and of
present forecasts against future performance. Accuracy cannot be tested by precise measurement but
buy judgment.

(ii) Plausibility:

The executive should have good understanding of the technique chosen and they should have
confidence in the techniques used. Understanding is also needed for a proper interpretation of
results. Plausibility requirements can often improve the accuracy of results.

(iii) Durability:

Unfortunately, a demand function fitted to past experience may back cost very greatly and still fall
apart in a short time as a forecaster. The durability of the forecasting power of a demand function
depends partly on the reasonableness and simplicity of functions fitted, but primarily on the stability
of the understanding relationships measured in the past. Of course, the importance of durability
determines the allowable cost of the forecast.

(iv) Flexibility:

Flexibility can be viewed as an alternative to generality. A long lasting function could be set up in
terms of basic natural forces and human motives. Even though fundamental, it would nevertheless
be hard to measure and thus not very useful. A set of variables whose co-efficient could be adjusted
from time to time to meet changing conditions in more practical way to maintain intact the routine
procedure of forecasting.

(v) Availability:

Immediate availability of data is a vital requirement and the search for reasonable approximations
to relevance in late data is a constant strain on the forecasters patience. The techniques employed
should be able to produce meaningful results quickly. Delay in result will adversely affect the
managerial decisions.

(vi) Economy:

Cost is a primary consideration which should be weighted against the importance of the forecasts to
the business operations. A question may arise: How much money and managerial effort should be
allocated to obtain a high level of forecasting accuracy? The criterion here is the economic
consideration.
(vii) Simplicity:

Statistical and econometric models are certainly useful but they are intolerably complex. To those
executives who have a fear of mathematics, these methods would appear to be Latin or Greek. The
procedure should, therefore, be simple and easy so that the management may appreciate and
understand why it has been adopted by the forecaster.

(viii) Consistency:

The forecaster has to deal with various components which are independent. If he does not make an
adjustment in one component to bring it in line with a forecast of another, he would achieve a whole
which would appear consistent.

Conclusion:

In fine, the ideal forecasting method is one that yields returns over cost with accuracy, seems
reasonable, can be formalised for reasonably long periods, can meet new circumstances adeptly and
can give up-to-date results. The method of forecasting is not the same for all products.

There is no unique method for forecasting the sale of any commodity. The forecaster may try one
or the other method depending upon his objective, data availability, the urgency with which forecasts
are needed, resources he intends to devote to this work and type of commodity whose demand he
wants to forecast.