After reading this article we will learn about:- 1. Meaning of Demand Forecasting 2. Importance of Demand Forecasting 3. Demand (Sales) Forecasting Periods 4. Factors Affecting5. Methods of Estimating Future Demand 6. Demand Forecasting of New Products 7. Criteria 8. Procedure.
- Meaning of Demand Forecasting
- Importance of Demand Forecasting
- Demand (Sales) Forecasting Periods
- Factors Affecting Demand (Sales) Forecasting
- Methods of Estimating Future Demand
- Demand Forecasting of New Products
- Criteria of Good Forecasting Method
- Demand/Sales Forecasting Procedure
1. Meaning of Demand Forecasting:
Accurate demand forecasting is essential for a firm to enable it to produce the required quantities at the right time and arrange well in advance for the various factors of production e.g., raw materials, equipment, machine accessories etc. Forecasting helps a firm to access the probable demand for its products and plan its production accordingly. Forecasting is an important aid in effective and efficient planning.
It reduces the uncertainty and making the organization more confident of coping with the external environment. The increasing availability of economic data, the continuous improvement of technique and the expanded computational ability provided by the computer made it possible for firms to forecast their demand/sales with considerable accuracy.
Accurate demand forecasting is essential for a firm to enable it to produce the required quantities at the right time and arrange well in advance for the various factors of production.
According to Henry Fayol, “the act of forecasting is of great benefit to all who take part in the process and is the best means of ensuring adaptability to changing circumstances. The collaboration of all concerned lead to a unified front, an understanding of the reasons for decisions and a broadened outlook”.
2. Importance of Demand Forecasting:
The importance of demand/sales forecasting can be understood by the following lines:
1. Helpful in deciding the number of salesmen required to achieve the sales objective.
2. Determination of sales territories.
3. To determine how much production capacity to be built up.
4. Determining the pricing strategy.
5. Helpful in deciding the channels of distribution and physical distribution decision.
6. To decide to enter a new market or not.
7. To prepare standard against which to measure performance.
8. To assess the effect of a proposed marketing programme.
9. To decide the promotional mix.
10. Helpful in the product mix decisions relating to width and length of product line.
3. Demand (Sales) Forecasting Periods:
Demand forecasting is done for a definite period. The period can be one month, three month, one year, two years, five years, ten years etc. Generally, organisations are involved in forecasting the demand for one year and taking that demand forecast as a base, the demand for 6 months, 3 months and one month is derived.
So demand forecasting is of two types on the basis of periods:
1. Short run demand forecast.
2. Long run demand forecast.
1. Short Run Demand Forecast:
Its period ranges from one week to six months.
Following important decisions are taken under short run demand forecasting:
(a) Evolving suitable production policy so as to avoid the problem of over production and under production.
(b) Determining appropriate price policy so as to avoid an increase when the market conditions are expected to be weak and a reduction when the market is going to be quite strong.
(c) Forecasting short term financial requirements. Cash requirements depend on sales level and production operations. Sales forecasts enable arrangement of sufficient funds on reasonable terms well in advance.
(d) Setting sales targets and establishing controls and incentives. If targets are set too high, they will be discouraging sales man who fail to achieve them; if set too low, the targets will be achieved easily and hence incentives will prove meaningless.
(e) Helping the firm in reducing cost of purchasing raw materials and controlling inventory.
2. Long Run Demand Forecast:
The period of this type of forecasting ranges from one year to five years. This type of forecasting is generally done for a product line rather than for an individual product.
The purpose of long run demand forecasting includes:
(a) New unit planning or expansion of an existing unit. A long term demand forecasting helps to plan for the new units or at the same time existing units to expand their activities. A multi-product firm must determine total demand situation and the demand for different items.
(b) Planning for long term financial requirements. If the demand is more and it takes long term, then for such long term financial requirements could be planned and made available.
(c) Planning for manpower requirements under the long term demand, manpower is mostly required. For this purpose, persons have to be trained.
4. Factors Affecting Demand (Sales) Forecasting:
The following factors are to be considered for while going demand forecasting:
1. Purchasing power of customers
4. Replacement demand
5. Credit conditions
6. Conditions within the industry
7. Socio economic conditions.
1. Purchasing Power of Customers:
This is determined by disposable personal income (personal income minus direct taxes and other deduction). Some people suggest the use of discretionary income in place of disposable income.
Discretionary income can be estimated by subtracting three items for disposable income, viz., inputted income, and income in kind, major fixed out lay payments such as mortgage debt payments, insurance premium payments, and rent and essential expenditures such as food and clothing and transport expenses based upon consumption in a normal year.
Discretionary income can be quite an important determinant in case of consumer non-durables which are luxuries.
This involves the characteristics of the population, human as well as non-human, using the product concerned. For example, it may pertain to the number and characteristics of children in a study of the demand for toys or the number and characteristics of automobiles in a study of the demand for tyres.
In fact, it involves distinguishing between the total market demand and market segments. Such segments may be derived in terms of income, social status, sex, age, male-female ratios, urban rural ratios, educational level, geographic location etc. The segment when quantified can be used as an independent variable affecting the demand for the product in question.
The price factor is another important variable to be included in demand analysis. Here, one has to consider the prices of the product and also its substitutes and complements. One may also consider the price differences between the product concerned and its substitutes and complements.
Price as a determinant of the volume of sales of consumer non-durables is sometimes more important through cross elasticity (involving substitute products) than it is directly in terms of price elasticity. Direct price elasticity can be expected to be more important with respect to those consumer non-durables which are capable of shortage and are free from risks of change in styles.
4. Replacement Demand:
The total demand consists of:
(i) New owner demand, and
(ii) A replacement demand.
The replacement demand tends to grow with the growth in the total stock with the consumers. Once a person gets used to a thing, he is unlikely to give it up at some future date. This makes replacement demand regular and predictable. For certain established products, life expectancy tables are been prepared in developed countries in order to estimate the average replacement rates.
When purchasing power increases, the scrap-page rate is lower. But as production catches up, the scrap-page tends to increase. The total demand is symbolically stated as D = N + R where N is new owner demand and R is the replacement demand. Each of these independent variables may be for casted separately.
The purchasing power, the number of families and some other factors depending on the product concerned, set an upper limit to the maximum or the optimum ownership level. It is the level towards which the actual volume of consumer stock tends to gravitate. The difference between optimum and the actual stock shows the growth potential of the demand for durable goods.
5. Credit Conditions:
The availability of credit and hire purchase facility tends to push up the demand for consumer durables. In India, for consumer durables like, refrigerators television, scooters etc., hire purchase facility is available. In western countries, the extension of credit is used as sales promotion measure.
Among the manufacturers, the Indian sewing machine company the manufacturers of singer, claim to have pioneered hire purchase in India (Business India). Hawkins pressure cookers are also available on hire purchase basis. The intensified competition between car and two wheeler manufactures has led to many firms extending credit for their purchase.
6. Conditions within the Industry:
The sales of a company is the part of the total sales of industry. If the conditions of the industry changes then the sales of each of the firm in the industry is affected. All the times the new marketers enter the market and some eclipse.
It is also to be decided about the position of our firm in the industry whether it has the leadership status or followers status or another. For example, if the prices of the product by a firm is reduced than there is an impact on other firms. Same is the case with promotion and distribution. All these factors affect the demand forecasting of the product.
7. Socio Economic Conditions:
Socio economic conditions of the country also affects the sales forecasting. They may include total national income, per capita income, standard of living of the masses, education, inflation, deflation etc. For instance, if the prices are rising sharply and the production is not increasing to cope the demand then it will be difficult for the public to satisfy their wants.
It will lead to the reduction in demand and thereby the demand forecast will be affected on the contrary. If there is a rapid increase in the per capita income along with increase in production, the demand will increase and thereby by the demand forecast will be affected.
5. Methods of Estimating Future Demand:
These are variety of methods and techniques for forecasting demand/sales. Which one or ones to use depends on factors such as the cost involved, the forecast’s time period, the market’s stability or volatility and the availability of personnel with forecasting skills. Some techniques are qualitative while others are highly quantitative.
The demand/sales forecasting methods include:
1. Survey of buyer’s intentions/opinion survey method.
2. Sales force composite method/collective opinion method.
3. Executive judgment/jury of executive opinion method.
4. Delphi method.
5. Time series analysis.
6. Market test method.
7. Correlation method.
1. Survey of Buyer Intention:
Customers may be asked to communicate their buying intentions in a coming period. This requires identifying potential buyers and asking them if they intend to buy a certain product during a specific future time period and if so, how many units and from whom will they buy. Survey of this type is used especially for industrial products’ demand forecasting.
1. Method is suitable for industrial product demand forecasting.
2. Surveys are sometimes used for forecasting demand of a new product. People may have need for a product are asked if they would buy it. These surveys often are conducted before the product is produced in large quantities to determine if the marketer really has a marketable product.
1. It is very expensive and time consuming.
2. A number of biases may creep into the surveys. If shortages are expected, customers may tend to exaggerate their requirements.
3. This method is not very useful in the case of house hold customer goods because of the irregularity in customer’s buying intentions, their inability to foresee their choice when faced with the multiple alternatives and the possibility that the buyers’ plans may not be real but only wish full thinking.
2. Sales Force Composite Method/Collective Opinion Method:
In this method, the sales men are required to estimate expected sales in their respective territories in a given period. Then the individual sales force forecasts are combined to produce the total company forecast. This method is used based on the assumption that sales persons are closest to the customers and have direct contact with the customers.
1. The forecasts are based on first-hand knowledge of salesmen.
2. This method may prove quite useful in forecasting sales of new products especially in the industrial market.
3. This method is simple.
1. It is a completely subjective method.
2. The sales person may give the lower estimates if the estimates alone are used to set their sales quotas.
3. Sales persons may be unaware of the broaderer economic changes likely to have an impact on the future demand.
4. The sales people are more concerned with making sales than with forecasting sales, which, to them may seem like needless paper work.
3. Executive Judgement/ Jury of Executive Opinion Method:
It involves combining and averaging the sales projections of executives in different departments to come up with a forecast. It they are experienced and knowledgeable about the factors that influence the sales, and if they are current on market developments, the approach can work.
1. Forecast may be made quickly and economically.
2. Much more factual than made from consumer opinion and sales force method.
1. It is very subjective and hence forecast lacks scientific reality.
2. The executives may rate recent experiences more heavily than more distant once which may result in too much optimism or pessimism regarding future sales.
4. Delphi Method:
It consists of an attempt to arrive at a consensus in an uncertain area by questioning a group of experts repeatedly until the responses appear to converge along a single line (consensus). The participants are supplied the responses to previous questions from others in the group by the coordinator.
The coordinator provides each expert with the responses of the others including their reasons, each expert is given the opportunity to react to the information or considerations advanced by others. Delphi Method was originally developed at Rand Corporation in the late 1940s by Olaf Helmer, Dalkey and Gorden and has been successfully used in the area of technological forecasting i.e., predicting technical change.
5. Time Series Analysis:
Time series analysis is based on extrapolation, which is the process of projecting a past trend or relationship into the future in the belief that history will repeat itself. Unfortunately, this is not always the case, especially in the longer term.
Hence, the importance of making assumptions about future events which may disturb previous patterns. Hence also the relevance of qualitative forecasting as described below, which attempts to predict the future without relying on statistical analysis of past events.
Components of Time Series Analysis:
The components of time series analysis are:
1. Cycle, which comprises the wave like movement of sales which react to periodic events or swings in economic activity.
2. Trend, which is found by fitting a straight or curved line through past sales.This process is known as trend fitting.
3. Erratic events, which include strikes or any major disaster that is unpredictable and needs to be removed from past data.
4. Season, which is the consistent pattern of sales movement during the year, for example, Christmas for the retail trade.
All these components are taken into account in time-series analysis using the techniques of trend fitting, smoothing and decomposition.
(A) Trend Fitting:
A projection is best made from a reasonably long series of data as shown in Fig. 5.2. There are three basic shapes of trend lines (Fig. 5.2, 5.3, 5.4, 5.5):
1. Linear trends which are straight lines as in Fig. 5.2 increasing by about the same amount each period.
2. Exponential trends which increase by the same percentage each year. Unless plotted on semi log paper they form a curve as shown in Fig. 5.3
3. S-shaped curves where typically, as illustrated in Fig. 5.4 Sales build up slowly after a product launch, accelerate as the product takes on and then ease off as maturity is achieved.
This pattern corresponds broadly with the initial stages of the product life cycle. The S-shaped curve can take other forms, for example a heavily promoted product may start very rapidly before easing off and finally declining, as illustrated in Fig. 5.5.
If sales fluctuate considerably during the year it may be desirable too smooth out the peaks and hollows to produce a recognizable trend as a basis for a projection.
The two most commonly used smoothing techniques are:
1. Moving Averages:
Which are calculated by taking a period say, three months. The sales are totaled for the period and divided by 3 to produce the average per month. When the next monthly sales figures are available, they are added to the previous total, but the sales for the first of the original three months are deducted.
The residual figure is divided by 3 to produce the moving average. Moving averages can be plotted on to a chart in the same way as raw sales figures, and trends are then extrapolated.
2. Exponential Smoothing:
This technique takes into account the greater significance in forecasting of recent trends by progressively weighting them more heavily. This produces an exponential curve.
(C) Decomposition Analysis:
By definition, smoothing a trend removes seasonal variations which are therefore not reproduced in the projection. But a company has to take account of such variations in its trading pattern when making sales plans and it is, therefore, useful to restore them by the technique of decomposition analysis.
This is described in detail by Bolt, but essentially involves:
1. Taking the seasonal element out of past trends.
2. Projecting the seasonal variations for the same period
3. Adjusting the de-seasonalised projection to take account of forecast seasonal movements.
4. Projecting the de-seasonalised trends for the period of the forecast. Time series extrapolation by short cut formula
A simple formula for predicting next year’s sales uses the per cent of sales increase or decrease of this year compared to last year:
Next year’s sale = This year’s sales x (This year’s sales/Last year’s sales)
Thus, if sales this year is 80, 00,000 and last year were 60, 00,000 the prediction of sales for the next year would be.
Next year sales = 8 x (816) = 10.67 = 1, 06, 70,000 units.
a. Simple trend analysis is for products with a history of stable demand than for products with erratic sales patterns.
a. The method cannot be used to forecast sales of a new product because past sales data are absent.
(6) Market Test Method:
In a market test the firm distributes the product in one or more markets to total potential customer response to the marketing mix. The market test measures actual sales not intentions to buy. If test markets are selected wisely and the test is conducted properly, the marketer can generalize test experience to the entire market and develop a demand/sales forecast.
1. It is very useful when surveys of buyer intentions are too costly or the data gathered is of questionable value.
2. The method is generally used to forecast demand for new products. However, they can also be used to forecast sales of existing products that being into the new geographical areas.
3. Market tests are also used to measure response elasticity to various levels of marketing.
1. Market tests are expensive and time consuming.
2. There is no guarantee. That buyer response in the test market will continue by the period of the test, or that test results will be duplicated in other markets.
(7) Correlation Method:
The method is based on historical sales data. When there is a close relationship between sales volume and a well-known economic indicator, correlation method can be used.
The marketer could develop a mathematical formula that describes the relationship between sales and independent variable and by plugging needed information into the formula, could than forecast sales on the basis of this independent variable.
6. Demand Forecasting of New Products:
Demand forecasting of new products is little bit difficult than forecasting demand for existing product. Its reason is that the product is not available and no historical data is available. In these conditions the forecasting is being done keeping in view the inclination arid wishes of the customers to purchase.
For this a research is being conducted but there is a problem because it is also very difficult for the customer to say anything without seeing and using the product before. So it is very difficult to forecast the demand for new products.
For forecasting here we base our estimate on the conventional methods which are as follows:
1. Evolutionary approach
2. Substitute approach
3. Market testing approach
4. The potential consumer approach.
1. Evolutionary Approach:
This method is based on assumption that the new product is the form of continuous improvement of the old one. The demand is for-casted as the basis of the demand of the old product. This method is only appropriate when the marketer is sure that the customers would take the new one as the improved version of the old one.
2. Substitute Approach:
This method is based on assumption that the new product is substitute to previous product and fulfill the same objective of the customers as by the previous product. On this basis it can be calculated that how far the new product would take the place of old one and on this basis the forecasting is done.
3. Market Testing Approach:
When product is quite new in the country, or good estimates are not available or buyers do not prepare their purchase plan, this method is very often adopted. Under this method, seller introduces his product in a part in the market segment for quite sometimes and makes the assessment of sales for the whole segment or the market on the basis of results of test sales.
1. It is best when a new product is introduced in the country for the first time.
2. Sales forecast is based on actual results hence forecast is more reliable.
3. During test period any defect in the product may also come in the knowledge of the sales executive or production executive which may be removed immediately to make the product successful in the market when it is fully commercialized.
1. Sales forecast data are projected on the basis of results of a part of the segment or the market.
2. It takes long time to test the market.
4. The Potential Consumer Approach:
If the new product is absolutely unique that cannot be compared with the existing products, then the forecaster must attempt to determine who the users might be potential consumer should be described and properly classified on the basis of appropriate segment variables e.g., income, age, statues, occupation, sex and so on.
Accordingly the size of each target market should be estimated. Thus a forecaster may be able to estimate obtainable sales volumes of the new product.
7. Criteria of Good Forecasting Method:
Following criteria are generally used to evaluate the effectiveness and efficiency of a forecasting method:
1. Simplicity and Ease of Comprehension:
The technique should be simple to understand and easy to operate. Management must able to understand and have confidence in the techniques used. Complicated mathematical and statistical procedures may be avoided.
Durability of the forecasting power of a demand and functions depends on reasonableness and simplicity of functions fitted.
The method should be accurate to suit to the needs of the time.
Techniques should give quick results and useful information.
Costs must be weighted against the importance of the forecast to the operations of the business.
8. Demand/Sales Forecasting Procedure:
It involves the following steps:
Determining the objective and the purpose for which the forecasts are to be used.
Determining the relative importance of the factor which affect sales of each product.
Selecting the appropriate forecasting method.
Collecting and analysing the data.
Making assumption regarding effect of factor.
Making specific forecasts relating to the product and territories involved.
Periodically reviewing and reviving the forecasts.