Demand forecasting• A forecast is a prediction or estimation offuture situation under given conditions• Demand forecasting is different from demandestimation in the sense that forecastingpredicts about future trends of sales whileestimation tries to find out expected presentsales level.
Demand forecasting continue…..• Passive forecast: where prediction about futureis based on assumption that firm does notchange the course of its action• Active forecast: where forecasting is doneunder the condition of likely future changes inthe actions by a firm
Purpose of forecasting• Short run forecast: seasonal patterns are moreimportant. It helps in preparing sales policy,price policy, production planning to avoidunder and over stock conditions.• Long run forecast: it is helpful for capitalplanning.
Methods of forecastingMethods of forecastingOpinion Polling method Statistical methodconsumer’s survey fitting trend line methodsales force opinion least square methodexpert’s opinion moving averageexponential smoothing
Opinion survey/consumer’s survey• Relatively simple and practicable method forforecasting demand of new products• Opinions are collected from prospective buyersregarding their future consumption• Sampling technique is used to surveycustomers• From sample it is possible to forecast demandof targeted population
Expert’s opinion• In this method expert’s opinion is sought onthe future demand for product• It is biased and subjective• The accuracy of predicted demand depends onskill, expertise and experience of personmaking forecast• Method is useful for forecasting demand ofestablished product
Sales force opinion• Expected sales is estimated by distributorssurvey through questionnaire or can berequested from retail outlet• Company’s sales force can also give estimationof future demand• Many company heavily rely on judgment madeby their sales personnel• But this judgment may suffer from overoptimism or over pessimism
Delphi technique• It can make more realistic forecast• A panel of experts are asked sequentialquestion and from responses newquestionnaire is produced.• Opinions are collected from experts to arrive atreliable results• Each questionnaire demands a detailed opinionfrom each expert and then these opinions aresummarized to get result
Time series methods• Time series refers to past data arranged inchronological order as a dependent variable andtime as independent variable for ex.• This is called time series. This method does notstudy factors affecting demand. In this method allfactors that affect demand are grouped into onefactor ‘Time’ and demand is expressed as a seriesof data with respect to timeYear 1994 1995 1996 1997Demand 20 30 40 58
Fitting Trend Line by observation method• The given time series data are plotted on agraph paper by taking time on X-axis and theother variable on Y-axis.• A smooth line or curve, drawn through theplotted points would represent the trend of thegiven data.
Least Square method (Regression Analysis)• In regression analysis relation betweendependent variable (y) and independentvariable (x) can be expressed by equation:Y=a+bX
Moving Average• Past data can have fluctuations because ofseasonal variation and random variation• Averaging the demand for previous period isgoing to hide the trend• MA consists series of arithmetic meanscalculated from overlapping groups ofsuccessive elements of time series.
• The period of moving average should becarefully selected• Wrongly selected period will distort data.• Longer the period of M.A. greater is thesmoothing effect
Moving Average continue…• Each moving average is based on valuescovering a fixed time interval, called ‘period ofmoving average’ and is shown against centre ofthe period.• For the time series values Y1, Y2, Y3,… themoving average for period n is given as follows:
Moving average continue….• 1st value of M.A.= 1/n (Y1+Y2+Y3+…+Yn)• 2nd value of M.A.= 1/n(Y2+Y3+Y4+…+Yn+1)• 3rd value of M.A. =1/n (Y3+Y4+Y5+…+Yn+2)And so on…..
Continue….• When period of M.A. is odd the successivevalues of the moving average are placedagainst the middle period.• For ex. If n=7 then first moving average isplaced against 4th value, the second movingaverage is placed against 5th value and so on.• If the period of M.A. is even then centeringmethod is used
Exponential Smoothing method• Very popular approach for short termforecasting• Method determines value by computingexponential weighted system• The weights are so assigned that w liesbetween 0 and 1• The rate of smoothness depends on value of w.
• The smoothing scheme begins by settingsmoothened value equal to observed value for1st period that meansS1=Y1• And for succeeding time period t, smoothenedvalue St is found by equationSt= w.Yt + (1-w).St-1Where St = current smoothened valueYt = current observed valueSt-1 = previous smoothened value