Demand Forecasting Project planning and evaluation PDF

Preview

Summary

demand forecasting and techniques of demand forecasting...

Description

DEMAND FORECASTING When estimating of future conditions are made on a systematic basis, the process is referred to as forecasting, and the figure or statement obtained is known s forecast. Forecasting reduce the areas of uncertainty in management deciding making respect to costs, profit sales, production, pricing and investment etc.

Methods of forecasting-it can be classified into qualitative and quantitative methods. Qualitative Techniques are based on estimates and opinions. (1)

Sales force composite method: This method of demand forecasting relies on the judgments of sales personnel. The field level sales personnel are requested to offer their forecast in their respective geographic area, to their sales managers. It is assumed that each sales person is who is close to the customer or end use of the product knows its future needs best. The forecast of sales personnel are pooled together and the estimate given by each person is adjusted by applying appropriate weights and adjusted forecasts are combined to arrive at the composite forecast.

Advantage: 

The sales persons are close to the customer. They are most likely to known which product, customer will be buying in the near future and in what quantities.

Disadvantage: 

Individual biases of sales people may affect the sales forecasts (some are optimistic some are pessimistic).



If the firm uses individual sales persons estimate as a performance measures, sales people may deliberately under estimate their forecast so that their performance/targets can be achieved.

1

(2)

Market Research: This is the most direct approach to demand forecasting. It sets out to collect data in a variety of ways (surveys, interviews and so an) to test hypotheses about the market. Consumers are approached and asked to express their opinion of a particular product. Firms hire outside companies that specialize this type of forecasting. This method is used mostly for products research in the sense of looking for new production ideas, likes and dislikes about existing products, which competitive product within a particular class are preferred and so on. Data collection methods are surveys and interviews. The survey can cover all the consumers if the consumers are small in numbers (e.g. Medical practitioners, Industrial product). If the number of consumer is large, a selected group of consumer is chosen for the survey.

Advantage: 

It is based on information of the persons who are directly involved in the system.



It can be used on forecast new product demand where data is not available.

Disadvantage: 

Surveys can be expensive and time consuming.



It may not be possible to contact every customer or potential customer and opinions are obtained from sample customer which may lead to forecast error if the sample size is inadequate.



It is time consuming method.



Results depend upon the knowledge and skills of the surveyor.

(3)

Jury or Experts opinion: In this method experts in their particular field are requested to give their views on the likely demand for the product in future. They are the persons who have been dealing in this product and in related products for a long time and thus are able to predict the future trend. The experts give their opinion after weighing pros and cons of all factors affecting the product demand, and arrive at an estimate which is backed by knowledge and experience of experts. If the views

2

of more number of experts are obtained and if their views differ significantly, then a forecast can be safely arrived at by taking the average of the experts’ predictions. The idea of expert opinion is that, discussion by the group will produce better forecast than any individual. Jury forecasts are developed through open meetings with free exchange of ideas.

Advantage: 

Use of experience and knowledge of expert so more appropriate forecast.



Can be used for forecasting the demand for new products.



This method is very simple.

Disadvantage: 

Difficult to obtain consensus opinion of several experts.



Executive opinion can be costly because it takes valuable executive time.

(4)

Delphi Method: This is a group decision by experts in which individual expert acts separately. Their views are pooled together and an attempt is made to arrive at consensus. If the views of the experts differ significantly, the individual experts are fed with the views of other experts and they are asked to further analyse the problem and to revise their views in the light of views of the other in the group. The objective to consolidate the divergent expert opinions and to arrive at a compromise estimate of future demand. Procedurally, a moderator creates a questionnaire and distributes it to participants. Their responses are summed and give back to the entire group along with a new set of questions estimates of forecast of other expert with underlying assumptions. The important aspect of Delphi technique is that experts who offer their opinion do not have face to face interaction and hence they are free to express their views. Hence this technique gives more accurate result as compared to Jury of Experts’ opinion method.

3

Procedure of Delphi method: 1. Choose the experts to participate. There should be a variety of knowledgeable people in different areas. 2. Through a questionnaire (or e-mail), obtain forecasts from all participants. 3. Summarize the results and redistribute them to the participants along with appropriate new questions. The participants are to revise their estimate in the light of forecast by others. 4. Summarize again, refining forecast and conditions and again develop new questions. 5. Repeat step 4 if necessary. Distribute the final results to all participants.

Advantage: 

The method can be used to develop long range forecast of production demand and process production demand forecast.

Disadvantage: 

It requires lot of time-time consuming method.



Difficulty in achieving consensus.

Quantitative methods (Time Series Projection methods) of Demand forecasting 1. Trend Projection Method

2. Moving average method: a moving average forecast uses a number of most recent historical actual data value to generate a forecast. The moving average (simple) for number of period is calculated as: Ft (forecast for the period coming) = At-1+ A t-2 + -----------+ At-n N

Ft = Forecast for the coming period n = No. of periods to be averaged. 4

At-1 = Actual occurrence in the past period At-2, At-3 and At-n = Actual occurrence two periods ago, three periods ago etc.

This method is used to estimate the average of a demand time series and remove the effects of random fluctuations. It is most useful when demand has no trend seasonal when demand has no seasonal fluctuations. In this method, if we use period moving average, the average demand for the n most recent time period is calculated and used as forecast for the next time period for the next period, after the demand is average is replaced with the most recent demand and the is recalculations illustration: Month

Actual Demand

Forecast based on simple moving average

(Period) 1 2 3 4

d1 d2 d3 d4

5

d5

6

d6

7

d1 + d2 + d3 (forecast for month 4) 3 d2 + d3 + d4 (forecast for month 5) 3 d3 + d4 + d5 (forecast for month 6) 3 d4 + d5 + d6 (forecast for month 7)

d7

Illustrations: If we want to forecast june with a five month moving average period. We can take the average of jan, feb, March, april and May when june passes, the forecast for july would be average of feb, march, april, may and june. It is important to select the best period for moving average. The main disadvantage in calculating a moving average is that all individual elements must be carried as data because a new forecast the earliest data for a 3 or 6 period moving average this is not serve. But plotting a 60 day moving average for the usage of each of 20,000 items in inventory would involve a significant amount of data.

5

Weighted moving Average: Whereas the simple moving average gives equal weight to each component of the moving average database, a weighted moving average allows any weights to be placed on each element, providing that the sum of all weight equals one. The formula for a weighted moving average is

Ft = W, At-1, + W2 At-2 + ----------- Wn At-n

Where W1 = Weight to be given to the actual occurrence for the period t-1 W2 = Weight to be given to the actual occurrence for the period t-1 N = Total no. of forecast ∑n wi= 1 (sum of all weight must equal) i=1

For example a departmental store may find that in a four months period, the best forecast is derived by 40% of the actual sales for the most recent month, 30% of two months ago, 20% of three months ago and 10% of four months ago. If actual sale was as follows, forecast the demand in the month of 5.

Month 1 100

F5 =

Month 2 90

Month 3

Month 4

105

Month 5

95

?

0.4 (95) + 0.3 (105) + 0.2 (90) + 0.1 (100)

=

38+31.05+18+10

=

97.5

Choosing weight: Experience and hit and trial methods. As a general rule, the most recent past is the most important indicator of future. Therefore it should get higher weighted and if data are seasonal, more weight can be assigned to the months if season.

6

EXPONENTIAL SMOOTHING: In the previous methods of forecasting (simple and weighted moving average) the major drawback is the need to continually carry a large amount of historical data. As each new piece of data is added in these methods, the new forecast is calculated. In many applications, the most recent occurrence are more indicative of future than those in the more distant past. If this premise is valid- than the importance of data diminishes as the past becomes more distant, then exponential smoothing is the most logical and earliest method to use.

In exponential smoothing method, only three pieces of data are needed to forecast the future, the most recent forecast, the actual demand that occurred for that forecast period and a smoothing constant. The smoothing constants determine the level of smoothing. The value of is determined both by the nature of the product and the managers sense of what constitute a good response rate. For example if a firm produces a standard item relating stable demand, the reaction rate to differences b/w actual and forecast demand would tend to be small. However, if the firm is expecting growth, it would be desirable to have a high reaction rate, may be 15 to 30% points, to give greater importance. The equation for a single exponential smoothing forecast is Ft = Ft-1 + α (At-1 - Ft-1) Where

Ft = The exponentially smoothed forecast for period t. Ft-1 = The exponentially smoothed forecast made for prior period. At-1 = Actual demand in the prior period. α = The desired response rate or smoothing constant.

This equation states that the new forecast is equal to the old forecast plus a portion of error (the difference b/w the previous forecast and what actually occurred).

Illustration: Assume that the long run demand for a product under study is relating stable and a smoothing constant α is considered 0.05. Assume that last month forecast (F t-1) was 1,050 units. If 1,000 actually were demanded, rather than 1,050, the forecast for this month would be Ft = Ft-1+ α (At-1 – Ft-1)

7

= 1,050 + 0.05 (1,000-1,050) = 1,050 + 0.05 (-50) = 1,047.5 units

Casual Methods of Demand Forecasting 1. End Use method: this method of forecasting is used for forecasting the demand for intermediate products. An intermediate product can have more than one uses, resulting in more than one final product. The demand for the various possible final products is projected. The likely consumption level at each of the final product is determined the consumption coefficient for the various uses. Consumption coefficient is the number of intermediate products used in one final product. Projected demand for the

= ∑ consumption coefficient * Projected output for

Intermediate product

the final product

Where n= the no. of final products in which the intermediate product finds its use. For example two wheeler automobile horn is an intermediate product. Is has no independent use of its own. It becomes useful when it is attached to the final products viz. the two wheeler automobiles. A horn can find its use in luna, scooters and motorbikes etc. which are the different end products. The consumption coefficient for horn is 1 since every unit of two wheelers is fitted with only one horn. If the output of different varieties of vehicles can be projected, we can also project the demand for intermediate product. Final Products

Consumption

Projected ouput for Projected

Luna Scooter Bikes

Coff 1 1 1 Total

final products 20,000 40,000 50,000 1,10,000

2. Chain Ratio Method

8

demand

for

intermediate product (Horn) 20,000 40,000 50,000 1,10,000

This method makes use of secondary data for forecasting the demand for a particular product. Macro level data is gathered which is reduced sequentially by applying appropriate reduction factors. For example let a company has proposal to manufacture mopeds to suit the requirements of female customers and decides to use chain ratio method to assess the demand. The following steps are used for assessment. Population of the target market:

4,00,00,000

Proportion of females in the population:

0.49

Total female population :

1,96, 00,000

Proportion of employed women in female population:

0.15

Number of employed women :

29, 40, 000

Proportion of college students in female population:

0.19

Proportion of employed women who can afford to buy a scooter:

0.55

Number of potential customers from employed women:

10, 99, 560

Proportion of female college students who can afford to buy a scooter:

0.30

Number of potential customers from college students:

8,71, 416

Total potential customers for scooters:

19,70, 976

Proportion of market share the firm is estimated to capture:

0.20

Estimated sales potential:

3,

19,195

3. Consumption Level Method This method is used for those products that are directly consumed. This method measures the consumption level on the basis of elasticity coefficients Income Elasticity: This reflects the responsiveness of demand to variations in income.

∆d d ∆I I

E=

∆d d

*

I /∆ I

9

The information on Income elasiticity of demand along with projected income is used to obtain a demand forecast. Example from the book. Price Elasticity of demand : It reflects the responsiveness of demand to variation in price.

4. Leading Indicator Method When the estimation on certain time series is done through observation (indicators) on another time series, then that method is known as barometric method of demand forecasting. This is the method that makes use of various indicators to predict the future. What is meant by economic indicators? Economic indicators refer to the statistical data or information relating to various economic areas. We understand that the business cycle goes through various ups and downs. The analysis or understanding of the business cycles in extremely important because it would show where exactly the economy is heading to. These indicators help in understanding how the economy is performing and also gives a sense of how the performance would be in the upcoming times. These indicators can be grouped into three types on the basis of their timings with respect to the happening of the events. Following are the types of indicators: 

Leading indicators



Coincident indicators



Lagging indicators Leading indicators: These indicators as the name suggest move ahead of the happening. In other words when an even that has already happened is used to predict the future event, then the already happened even would act as a leading indicator. For instance the data relating to working women would act as a leading indicator for the demand of working women hostels. Though such leading indicators provide a way to understand the future demand, their major drawback is that they may not be always precise. What are the prominent examples of leading economic indicators? They would be data related to mean week hours of work put in by the workers, producers’ fresh orders for consumer goods, consumer expectations index, producers’ fresh orders of capital goods etc.

10

Coincident indicators: These are those indicators that take place simultaneously to the happening. These coincident indicators would include data relating to people employed in non-agricultural sectors, production of the industrial sector, personal income etc. These indicators too depict the state of the economy. For instance if the data related to industrial production show strong numbers, then it shows that the economy is performing well. On the other hand disappointing industrial production numbers would reflect poor state of the economy. Lagging indicators: These indicators are those which take place after the happening. These indicators are essential to understand how the economy would shape up in the future because these follow the economic cycle. In other words these indicators show the way to the future. Hence lagging indicators are those which are the most important ones and are extremely useful in predicting the future economic events. Inflation and data relating to unemployment levels are the top indicators that help in understanding or analysing the performance of the economy.

11...