What is Demand Forecasting – Demand forecasting consists of two words – demand and forecasting. Demand Forecasting is the estimation of the potential demand or potential sale of a commodity in a given period of time, which can be expressed in terms of price or quantity or both.
Methods of Demand Forecasting
(A) Qualitative Methods – These methods rely essentially on the judgement of experts for translating qualitative information into quantitative estimates. The main methods are:
- Jury of Executives Opinion Method – In this method, opinions of a group of experts on expected future sales are collected and combined them into a sales estimate. The executives selected as experts have knowledge about the market conditions, capacities and fluctuations in the market. This method is easy and less time consuming. But, its reliability is questionable due to personal biasness of experts.
- Delphi Method – This method is used to draw conclusion on the basis of opinions of a group of experts with the help of a mail survey. In this method, the identity of the experts is kept secret. A questionnaire is sent by mail to a group of experts and asked them to express their views and responses. The responses received from experts are summarised. This method is very economical and suitable for new products. But, it is time consuming and co-ordination is difficult.
(B) Quantitative Methods – The important quantitative methods in estimating demand are as follows:
- Trend Projection Method – This method involves determining the trend by analyzing past data and projecting future demand. In trend projection method, the most commonly used relationship is the linear relationship. For this purpose, least square method is used. In this method, estimates are based on statistical methods and objectivity. But, this method is more complicated than the methods discussed earlier.
- Moving Average Method – In this method, forecasting is based on the average of sales of several preceding years. A method based on moving averages is more frequently used for estimating the seasonal variations. The choice of the length of a moving average is an important decision in using this method. It is the length of the moving average which determines the extent to which the variations are smoothed in the process of averaging.
- Exponential Smoothing Method – This method is used to estimate the short-term sales. This method is an improved form of Moving Average Method. In this method, forecasts are modified in the light of observed errors. Weights are allotted to the values of time series to calculate the weighted average. Highest weight is given to the latest data and lesser weight to the old data. The purpose to calculate weighted average is to minimize the difference between forecasted and actual data. The estimates taken in this method are more reliable and accurate.
(C) Casual Methods – Under casual methods, estimates are made on the basis of cause and effect relationship. The brief discussion of these methods is given below:
- Chain Ratio Method – The potential sales of a product may be estimated by applying a series of factors to measure aggregate demand. These factors are step-wise used to measure demand. This method uses a simple analytical approach to demand estimation. For example, a shaving blade manufacturing company estimates its potential sales on the basis of various factors such as adult male population in the country, proportion of males doing shave, life of a blade, potential market share, etc. However, its reliability is critically dependent on the ratios and rates of usage used in the process of determining the sales potential. While some of these ratios and rates of usage may be based on objective proportions, others will have to be subjectively defined.
- Consumption Level Method – This method is used where a product is directly consumed by consumers. In this method, consumption level is estimated on the basis of elasticity co- efficients. The important co-efficients are the income elasticity of demand and the price elasticity of demand. The income elasticity of demand reflects the responsiveness of demand to variations in income. In other words, demand tends to vary from one income group to another. The information on income elasticity of demand along with projected income be used to obtain demand forecast. On the other hand, the price elasticity of demand may measures the responsiveness of demand to variations in price. The future volume of demand may be estimated on the basis of the price elasticity coefficient and expected price.
- End Use Method – This method is useful to estimate the demand for intermediate products. The end use method is also called as consumption co-efficient method. It involves the following steps: Identify the possible uses of the product, Define the consumption co-efficient of the product for various uses, Project the output level for the consuming industries and Estimate the demand for the product.
- Leading Indicator Method – Leading variables are the variables which change ahead of other variables, the lagging variables. Firstly, changes are observed in leading indicators. Then, observed changes in leading indicators are used to predict the changes in lagging variables. But, it may be difficult to find appropriate leading indicators and the lead-lag relationship may not be stable over the time.