Prepared by Odwar Vincent-Lira University

DEMAND FORECASTING
Introduction
Demand forecasting is one of the fundamental managerial tasks. Generally, there is
uncertainty in every decision-making process. The producer of some goods or any other
decision-making authority or the government must keep in view the existing level of
demand for the product in question and estimate the prevalent gap between demand and
supply. The decision maker, whether a firm or a state planning agency, must not only
estimate the present level of demand but also forecast the demand for a future date.
Degree of risk depends upon the nature of business. All the risks cannot be completely
eradicated but by proper planning these risks can be minimized. Demand forecasting is also
one of the techniques to minimize the risk and uncertainty.

Concept of Demand Forecasting

 Forecasting means estimating future event or condition which is outside an
organization’s control and provides a basis for managerial planning.
 Forecasting of demand is the art of predicting demand for a product or a service at
some future date on the basis of certain present and past behavior patterns of some
related events. Please remember that forecasting is no simple guessing but it refers
to estimating scientifically and objectively on the basis of certain facts and events
relevant to the art of forecasting.

Features of Demand Forecasting

From the above discussions the following features of demand forecasting emerge:
1. Demand forecasting is based on past data and present positions.
2. Demand forecasting may be monetary or physical.
3. Demand forecasting gives basis to future planning.
4. Demand forecasting is made for a certain period.
5. Future sales and profit estimate can be made by demand forecasting.

1|Page
Importance/benefits of Demand Forecasting
Demand forecasting is important for every producer. He has to know the present level of
demand and also the increase that is expected to take place in the demand for his product
over time. Demand forecasts are generally useful for the following categories of decision
makers:-
1. Importance for the producers in improving the quality of their capacity plans, sourcing
plans and inventory plans can be made well in advance.
2. Importance for policy makers and planners.
3. Importance for estimating financial requirements.
4. Utility for determination of sales target & profit.
5. Regular supply of labor and raw material is made possible by demand forecasting.
6. Production planning is possible with the help of demand forecasting.
7.Efficient utilization of resources.
8.It reduces cases of stock outs and allow operating with lower inventory levels.

Limitations to or errors in forecasting

 There is always uncertainty in demand. All future events that have impacts on
demand cannot be reliable predicted.
 The further into the future the forecasts are made, the less reliable they are.
 Forecasts are less reliable on the detailed level than the on a general level. E,g. less
reliable for a single customers than for customer groups and on a daily level, the
forecasts are less reliable than on the weekly level.
Strategies for reducing errors or impacts of uncertainties in forecasting.
 Reduce production lead time. The more production lead time the more the error.
Ideally, the production lead time should be less than the demand lead time.
 Force a march between the production lead time and the demand lead time. Make a
customer demand lead time equals your production lead time.
 Simplify the product line. The more variety in product line, the more room for error.
 Standardize products and processes. Customization should occur close to the final
assembly point.
 Forecast more accurately
 Operate on a make to order basis instead of make to stock.

2|Page
Methods of Demand Forecasting
Demand forecasting is a very absorbing and difficult exercise. Consumer’s behavior is the
most unpredictable thing in the world because it is motivated and influenced by
multiplicity. Moreover; economist and statisticians over the years have developed several
methods of demand forecasting. Each of these methods has its relative merits and
demerits. Selection of the right method is essential to make demand forecasting accurate
and credible.
The methods of demand forecasting can be summarized in the form of qualitative and
quantitative methods as follows:

[A] Qualitative Method:-

Expert Opinion Method:- Under this method the researcher identifies the experts on the
commodity whose demand forecast is being attempted and probes with them on the likely
demand for the product in the forecast period. The word ‘Expert’ is a high powered term
but it should be taken to stand for those who possess the requisite expertise on the subject.

Delphi method. This method seeks the opinion of a group of experts through mail about the
expected level of demand. The responses so received are analyzed by an independent body.
The method thus takes care of the disadvantage of panel consensus where some powerful
individual could have influenced the consensus.

Survey Method:- According to this method a few consumers are selected and their views on
the probable demand are collected. The sample is considered to be a true representation of
the entire population. The demand of the sample so ascertained is then magnified to
generate the total demand of all the consumers for that commodity in the forecast period.
The selection of an opinion sample size is crucial to this method, while a small sample
would be easily managed and less costly.

Enumeration Survey Method:- Under this technique either consumers are divided in several
groups on the basis of income, age, sex, education or any other variable or they may be
divided according to geographical regions. Through appropriately selected sample design,
sample units are selected and data are collected either through direct interview or by

3|Page
mailing questionnaires. The results of sample survey may be reliable provided the sample is
representative of the population.
End Use Survey Method:- Under this method commodity that is used for the production of
some other finally consumable goods is also known as an intermediary good. While the
demand for goods used for final consumption can be forecasted using any other method the
end use method focuses on forecasting the demand for intermediary goods. Such goods can
also be exported or imported besides being used for domestic production of other goods.
For example milk is a commodity which can be used as an intermediary good for the
production of ice cream, yoghurt and other dairy products.
The demand for various products from milk can be generalized to calculate the projected
demand for any commodity.

[B] Quantitative Methods:-

These methods are based on historical Quantitative data. A statistical concept is applied to
this existing data about the demand for a commodity over the past year in order to
generate the predicted demand in the forecast period. Due to this reason these
Quantitative methods are also known as statistical methods.
A firm which has been in existence for some time will have accumulated considerable data
on sales pertaining to different time periods. Such data when arranged chronologically yield
time series. Time series relating to sales represent the past pattern of effective demand for
a particular product.
Such data can be used to project the trend of the time series. This can be done either
through graph or through least square method.

Least square method.

Following equation is used under Trend Projection Method:-
I Y = a+bx
II Y = na+bx
III xY = ax+bx2

Example-Given the following sales data from year 2018 to 2022

Years Sales (In UGX.)

4|Page
2018 120
2019 140
2020 150
2021 140
2022 170
Required: Find out the estimated sales for next five year i.e. 2023 to 2026.

Solution:
Years Sales Deviation
(N) (Y) (X) X2 XY
2018 120 -2 4 -240
2019 140 -1 1 -140
2020 150 0 0 0
2021 140 +1 1 140
2022 170 +2 4 340
N=5 Y =720 X=0 X2= 10 XY =100

Calculation of a, we have equation (II)

Y = na +bX
720= 5a+0
a =720/5 = 144
For finding b, we use equation (III)
xY=ax+bx2
100= 0+ b10
100/10=b
b=10
By keeping the value of a & b in equation (I)
Y = a+bx (a=144, b=10)
Y= 144+10X-- (IV)
On the basis of this equation (IV) we can find trend for next five years as follows:-
Years Deviation Sales Y=144+10X
(X) (UGX.)

5|Page
2020 -2 -
2021 -1 -
2022 0 -
2023 +1 -
2024 +2 - (Already Given)
2025 +3 Y(144+10(3)=174
2026 +4 184
2027 +5 194
2028 +6 204

Regression Method:- Under this method relationship is established between Quantity

demanded and one or more independent variables such as income, price of the related
goods, price of the commodity under consideration, advertisement cost etc. In regression, a
Quantitative relationship is established between demand which is a dependent variable and
the independent variable i.e., determinants of demand.
Let us suppose that we have two variables Y and X where Y is dependent on X. it can be
expressed in the form of an equation as follows:-Y=a+bx
In order to estimate the regression line we should first find the values of the constants a
and b from the regression equation Y= a+bx
Example: Given the sales data below,

Year 2019 2020 2021 2022 2023

I Income 100 110 140 150 200
Index
II Sales of 110 130 150 160 180
TV (000)

Required:
(i).The regression equation
(ii) Estimate sales of T.V. if the Index of income rises to 240 .
Solution:

6|Page
In order to estimate the regression line, we should first find the values of the constants a
and b

Hence the regression equation is:

Y= a+bx

b = n∑X1Y1 - (∑X1∑Y1)
n∑x12 –(∑x1 )2

= 5x1063 – 70x73
5x1042 -70x70

= 5315-5110
5210-4900

= 205
310
b =0.66

a = ∑Y1 -b∑X1
n
=73 -0.66x70
5
=73 -46.2
5
=26.8
5
a =5.36

Therefore Y = 5.36+0.66 x
If the Index of Income rises to 240, sales of TV will be estimated as follows:-
Y= 5.36+0.66x240
7|Page
5.36+158.4
163.76 Thousand.

Graphical Method- Under this method trend is estimated with the help of a graph. Time &
Quantity demanded are taken on both the axis and demand forecasting is made for future.
This method is completely subjective, as in this method graph is drawn and on the basis of
this graph demand forecasting is made. Expansion of this graph is completely imaginary &
subjective so it can be different for different persons. According to graphical method, the
past data will be plotted on a graph and the identified trend/ behavior will be extended
further in the same pattern to ascertain the demand in the forecast period.

Demand Forecasting Process

Process for demand forecasting depends on the scope of demand forecasting. We may
follow the following sequence in projecting the demand for a product:
1. Specifying the objectives- The person or agency assigned the task of forecasting the
demand must specify the purpose for which demand forecasts are being made.
2. Selection of Appropriate Method-Once the purpose of demand forecasting has been
specified, we must select the methods which will be used for the purpose.
3. Collection of Appropriate Data-The quality and adequacy of data will determine the
quality of our results and their reliability. As far as possible, data must be collected by
experienced persons.
4. Estimation and Interpretation of results- Having collected the relevant data we have to
compile them and obtain results manually or with the help of computers. These results
must be interpreted and their correspondence with the objective examined.
5. Evaluation of the Forecasts- If the method or model used in demand forecasting has
objectivity; we may expect to receive good results. Yet the result so obtained must be
verified by persons having professional acumen and expertise. However, the results of
operations may not match with the forecast results. This should be considered as errors in
forecast and strategies to minimize errors to forecasts should be utilized in that
circumstance.

8|Page
9|Page