Demand forecasting
economics
Reference page 100
Demand forecasting is the tool to scientifically predict the likely demand of a product in the future.
Choice of a forecasting technique depends on objectives, costs, time, nature of data, and complexity of the technique.
Forecasting Methods
Survey Method
Consumer's Intentions Survey method :
its further divide into two parts , 1. If the survey happens to be a census, then the demand forecast for total household
consumption is obtained simply by adding the intended demands of all households:
ID is intention demand
2)In case the survey was of a sample of households instead of all, then demand forecasts would have to be obtained
differently
it help both consumer and producers side and also in forecasting the demand of mix good (the good which used by both
producer side and consumer side )
Experts’ Opinion Survey Method :
1. simple : take average of individual guesses of different expert .
2. Delphi method : Delphi technique originally developed by Rand Corporation at the beginning of the cold War , to
forecast the impact of technology on welfare . In this method , a panel of carefully selected independent expert answer
questionnaire's in two or more rounds , at the end of which an anonymous summary of each expert opinion is provided .
this offer scope for revision of previous replies and the group eventually converges towards the correct answer .
market experiment :
It has two versions: actual and simulated.
Under the actual experiment(test market), shops are opened in different localities (places) and then consumers’ reactions
are observed and recorded. Different localities would include consumers with varying levels of income, caste and religion,
sex, age group, tastes and preferences, etc. Further, during the experiments, various prices could be tried to elicit
consumers’ reactions to price changes. If such an exercise is carried out with sufficient care with regard to the sample of
locations and probable prices, the researcher should have no difficulty in coming out with a demand function, indicating
quantities that consumers would demand at various levels of incomes, prices, and other relevant variables in the function.
Educational institutions organize marketing fairs to elicit such data from the visitors.
The market simulation method, also called consumer clinic or laboratory experiment technique, involves providing token
money to a set of consumers and asking them to shop around in a simulated market. The prices of various goods, their
quality, packaging, etc. vary during the experiments to observe consumers’ reactions to such changes. This generates
information which could be sufficient to estimate the demand function.
Conclusion : Of these two versions, the actual experiment method is more reliable than the simulated experiment one. This is
because the consumers have no stake in the latter and may not take the experiment seriously. As a result the data generated
will not be reliable, which would render the whole exercise futile. However, actual experiments, though desirable might be too
costly. Thus, the firm which is interested in following either version would have to debate the pros and cons before deciding.
Statistics Method :
Graphical method : Under this method, a graph of historical data on the variable under forecasting is drawn, it is then
extrapolated visually up to the forecast period, and finally the value of the variable in the forecast period is read out from the
graph to yield the requisite forecasts.
Time series Analysis :
Trend Projection:
By analysing historical demand data, this method identifies underlying patterns or trends (e.g., increasing demand for
eco-friendly products) and projects them into the future. It's particularly useful for long-term demand forecasts where
gradual changes are expected. Techniques like moving averages or regression analysis help make accurate
projections.
Linear Trend: when the time-series data reveals a rising or a linear trend in sales, the following straight line equation
is fitted:
S = a + bT
Where S = annual sales; T = time (years); a and b are constants.
ARIMA (Auto-Regressive Integrated Moving Average)** method:
1. Transform the Data (Stationarity): Convert the original time series (Y) into a stationary series (Z) by removing
trends or seasonality using techniques like differencing or logarithms.
2. Forecast Using ARIMA Model: Combine auto-regressive (AR) and moving average (MA) components to forecast
future values of Z. Specialized mathematical techniques are used to estimate the model's parameters.
3. Reverse the Transformation: Transform the forecasted values of Z back to the original scale (Y) to obtain the final
forecast.
Barometric Forecasting:
In barometric forecasting, we construct an index of relevant economic indicators and forecast future trends on the
basis of these indicators.
Leading Indicators:
These help forecast demand by providing early signals of shifts in the market. For instance, a surge in the Consumer
Confidence Index might predict higher demand for non-essential goods, as consumers feel optimistic about
spending.
The method involves three steps
(a) Identification of the leading indicator for the variable under forecasting.
(b) Estimation of the relationship between the variable under forecasting and its leading indicator.
(c) Derivation of forecasts.
Composite and Diffusion Indices:
Composite Indices combine multiple demand-related indicators to give a broad measure of market activity (e.g.,
combining data from sales trends, inventory levels, and consumer surveys to predict demand).
Diffusion Indices reflect the proportion of individual indicators that are experiencing growth, helping to measure the
breadth and consistency of demand changes across a market or sector.
