Demand Forecasting
Demand Forecasting
Aim/Purpose of the forecasting
1. Purposes of short-term forecasting Appropriate production scheduling. Reducing costs of purchasing raw materials. Determining appropriate price policy Setting sales targets and establishing
controls and incentives. Evolving a suitable advertising and
promotional campaign. Forecasting short term financial
requirements
Purposes of long-term forecasting Planning of a new unit or expansion of
an existing unit. Planning long term financial
requirements. Planning man-power requirements.
Demand forecastingIt involves determining the expected
level of demand during the period under consideration
Factors involved in Demand Forecasting
Undertaken at three levels:Macro-level Industry level eg., trade associations Firm level
Criteria of a good forecasting method
Accuracy – measured by (a) degree of deviations between forecasts and actuals, and (b) the extent of success in forecasting directional changes.
Simplicity. Economy. Availability. Maintenance of timeliness.
Length of forecasts
• Short-term forecasts – upto 12 months, eg., sales quotas, inventory control, production schedules, planning cash flows, budgeting.
• Medium-term – 1-2 years, eg., rate of maintenance, schedule of operations, budgetary control over expenses.
• Long-term – 3-10 years, eg., capital expenditures, personnel requirements, financial requirements, raw material requirements.
Forecasting Steps1. Identification of objective: what does one want to get from the
forecast
2. Determining the nature of goods under consideration: Different
categories of goods like consumer goods, durables and non-
durables, have their own characteristics and distinct demand
patterns
3. Selecting a proper method of forecasting: The selection of
appropriate method is based on type of data available, period for
which forecast is to be made etc.
4. Interpretation of results: A good forecast depends on the efficiency
in the interpretation of its results.
Methods of demand forecasting
No forecast can be expected to be cent percent correct
There are several methods of forecasting basically for three reasons:
1. No method is perfect and no method is useless
2. No method is best under all circumstances, and
3. The best method may not be available in particular situation due to constraint from data , time and money.
Forecasting techniques
Qualitative Techniques
Quantitative Techniques
Expert opinion
Method
Survey Methods
Complete Enumeration
Survey Method
Sample Survey Method
Sales force Opinion survey
Method
End Use
Survey
Method
Trend
Projection Method
Barometric Technique
Econometric Techniques
Regression Method
Simultaneous Equation Method
Qualitative forecasting is based on opinion & intuition.
Used when data are limited, unavailable, or not currently relevant
Quantitative forecasting uses mathematical models & historical data to make forecasts. Time series models are the most frequently used
among all the quantitative forecasting models.
Expert Opinion MethodTake the views of experts regarding the
demand in the futureExperts are informed persons who know the
product very well as they have dealing with it and related products for a long time
If the forecasting is based on the opinion of several experts, then it is known as panel consensus (or agreement)
One disadvantage: Powerful individual could have influenced the consensus
Delphi Method: This is the specialized form of panel opinion.
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
Advantages
(a)It is simple to conduct
(b)Can be used where quantitative data is not possible
(c) The forecast is reliable as it is based on the opinion of people who know the product very well
(d)It is inexpensive
(e) It takes little time
Disadvantages
(a)This is not a scientific analysis, it is based on mere guess of one or more persons
(b)The experts may be biased
(c) Forecast could be unfavourably influenced by persons with vested interests
Complete Enumeration Survey Method
Complete survey of all the consumers for the commodity
Interviews or questionnaires are used to ask consumers about the quantity of the commodity they would like to buy
Data collected and added up then arrive at the total expected demand for that product
Advantages(a)Quite accurate as it surveys all the
consumers of a product
(b)It is simple to use
(c) It is not affected by personal bias
(d)It is based on collected data
Disadvantages
(a)It is costly
(b)It is time consuming
(c) It is difficult and practically impossible to survey all the consumers
(d)Useful only for products with limited consumers
Sample Survey Method
Instead of surveying all the consumers of a commodity, only a few consumers are selected and their views on the probable demand are collected
Population
Sample
Advantages
(a)It is simple and does not cost much
(b)Since only a few consumers are to be approached, the methods works quickly
(c) The risk of handling a large number of data is reduced
(d)It gives excellent results, if used carefully
Disadvantages
(a)The conclusions are based on the view of only a few consumers and not all of them
(b)The sample may not be a true representation of the entire population
Advantages:(a)Perhaps the simplest of the forecasting methods
(b)It is less costly
(c)Collecting data from its own employees is easier for a firm than to do it from external parties
Disadvantages:
(a)Sales force may give biased views as the projected demand affects their future job prospects
(b)Sales force may not be expertise to predict the future demand.
Sales Force Opinion Method
Similar to the expert opinion methodInstead of external experts, employees of the
company who are a part of the sales and marketing teams are asked to predict future levels of demand
The sales force, who has been selling the product over a period of time, is considered to know the product and demand pattern very well
End Use Survey Method A commodity that is used for the production of
some other finally consumable good is known as an intermediary good
This method focuses on forecasting the demand for intermediary goods
Such goods can 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, paneer and other dairy products.
= Final consumption demand for milk
=Export demand for milk
=Import of milk
=Per unit milk requirement of the ice cream industry
=Output of the ice cream industry
notations are similar to for paneer
mcD
nnppiimmemcm oxoxoxIDDD .........
meD
mI
ix
iopp ox & ii ox &
Advantages:
(a)The method yields accurate predictions
(b)It provides sector wise demand forecast for different industries
Disadvantages:
(a)It requires complex and diverse calculation
(b)It is costlier as compared to other survey methods and is more time consuming
(c)Industry data may not be readily available
Quantitative Methods
Trend Projection Method
It is based on the assumption that the future is an extension of the past. Historical data is used to predict future demand.
The trend could be linear or curvilinearThere are two trend methods:Graphical methodAlgebraic method
Graphical method: The past data will be plotted on a graph
The identified trend will be extended further in the same pattern to ascertain the demand in the forecast period
In the figure trend 1 is linear, trend 2 is non-linear
Dem
and
Trend 2
Algebraic methodThis is also known as the least square methodThe demand and period data are fitted into a
mathematical equationSome of the most common trend equations
are:
1.Linear trend : Y=a + bX
2.Quadratic trend : Y=a + bX + cX2
3. Cubic trend : Y= a + bX + cX2 +dX3
The linear trend is the most widely used mode of time series analysis
Y = a + bX
Where, Y= Demand
X= Time period (number of years)
a and b are constants
a = Intercept
b = Slope of the line
The calculation of Y for any value of X requires the values of a and b. For this two normal equations are to be solved. These are:
∑Y= na + b∑X
∑XY = a ∑X + b ∑X2
Advantages:
1.It is very simple method
2.The method provides reasonably accurate forecasts
3.It is quick and inexpensiveDisadvantages:1. Can be used only if past data is available
2. It is not necessary that past trends may continue to hold good in the future as well
3. Does not consider any possible causal relationships that underlie the forecasted variable
Barometric Technique The Bhuj earthquake in January 2001, lead to a massive destruction of property & buildings in Gujrat.
This necessitated construction of buildings to rehabilitate the people of affected areas.
The construction was followed by a spurt in the demand for cement, fans, tube lights, etc.
Thus, construction of buildings leads to the demand for cement.
Here, construction of buildings is the leading indicator or the barometer
Erratic cyclical patterns in time series.
Movements of different economic variables
Correlation between two time series can of three types:
1. Second series moves ahead of the first series then second series is known as the leading series while the first series is
called lagging series.2. First series moves ahead of the second series then
first series is known as the leading series while the second series is called lagging series
3. If both of them move along with each other then the series are called coincident series
It uses the lead and lag relationship between economic variables for predicting the directional changes in the concerned variables.
This technique requires establishing the lead-lag relationship between the two series
Advantages:
1.It is simple method
2.It predicts directional changes quite accurately
Disadvantages:
1.It does not predict the magnitude of changes very well
2.The method can be used for short-term forecast only
Econometric TechniquesBoth economic theory & mathematical tools are
applied in this method
1. Regression Method:
Forecasting problems can often be analyzed with single equation econometric models. This is called the regression method. The relevant equation is:
Where, a, b, c, d and e are constants
=Demand for X, I= Consumer’s income
=Price of X, A= Advertisement outlay
= Price of its substitute product Y
yxx ePdAcIbPaD
xD
xP
yP
Advantages:1. As the method is based on causal relationships, it
produces reliable & accurate results
2. This method not only forecasts the direction but also the magnitude of the change
3. The method is quite consistent
Disadvantages:1. The method uses complex calculations
2. It is costly & time consuming
Simultaneous equation method
When the inter-relationship between the economic variables becomes complex, the use of single equation regression method becomes difficult
In such cases, forecasting of demand is done using multiple simultaneous equations
A detailed discussion of this method is not included in our syllabus