Part I THE BIG PICTURE Sales Management Resources: Estimating Potentials and Forecasting Sales
IMPACT OF SALES FORECASTS ON BUDGETING Sales forecasts Sales budget Production budget Direct labor materials and overhead budgets Cost of goods sold budget Budgeted profit and loss statement Sales and administrative expense budget Revenue budget
Figure SMR2-1 Relations Among Market Potential, Industry Sales, and Company Sales Company forecast Actual Forecast Custom time period Industry forecast Industry Sales Market potential Company potential BasicDemandGap CompanyDemandGap
Table SMR2-1 Data Used to Calculate Buying Power Index 2004 Effective Buying Income 2004 Total Retail Sales 2004 Estimated Total Population Amount ($000,000) Percentage of United States Amount ($000,000) Percentage of United States Amount ($000,000) Percentage of United States Buying Power Index Total United States $5,466, %$3,906, % % Atlanta Metro $ 99, %$ 69, % %1.7636
Table SMR2-2 Estimating the Market Potential for Food Machinery in North Carolina NAICCodeIndustry(1) Production Employees a (2) Number of Machines Used per 1000 Workers b Market Potential (1x2) 3112 Grain Milling Tobacco Mfg. 9, Beverages3, a The production employee data are from the 2002 Economic Census of Manufacturing, Geographic Area Series, North Carolina, p. NC1 & 2. The codes are the new NAIC codes b Estimated by manufacturer from past sales data.
Percentage Percentage of of FirmsPercentage of Firms that That Use Firms No MethodsUse Regularly Occasionally Longer Used Subjective Sales force composite 44.8% 17.2% 13.4% Jury of executive opinion Intention to buy survey Extrapolation Naïve Moving Average Percent rate of change Leading indicators Unit rate of change Exponential smoothing Line extension Quantitative Multiple regressing Econometric Simple regression Box-Jenkins Table SMR2-3 Utilization of Sales Forecasting Methods of 134 Firms
Table SMR2-4 Calculating a Seasonal Index from Historical Sales Data a Seasonal index is 58.0/9.25 = 0.73 Quarter1234 Four-Year Quarterly Average Seasonal Index a Four year sales of 1268/16 = average quarterly sales
Quarter 1234 Actual sales Naïve forecast Quarter 1234 Actual sales Naïve forecast Percentage forecasting error = forecast – actual actual Percentage forecasting error = = 36% 77 NAÏVE FORECASTS AND PERCENTAGE FORECASTING ERROR
Percent rate of change forecast Unit rate of change forecast Naïve forecast Moving average forecast Figure SMR2-2 Comparing Trend Forecasting Methods Sales Time Period
MEAN ABSOLUTE PERCENTAGE ERROR (MAPE)
where F t+1 = forecast for the next period S t = sales in the current period n= number of periods in the moving average CALCULATING A MOVING AVERAGE FORECAST
Quarter 1234 Actual sales Two-period moving average Quarter 1234 Actual sales Two-period moving average MOVING AVERAGE FORECASTING EXAMPLE
where = smoothed sales forecast for period t and the forecast for period t + 1 α= the smoothing constant S t = actual sales in period t -1 = smoothed forecast for period t – 1 CALCULATING AN EXPONENTIAL SMOOTHING FORECAST
Quarter 1234 Actual sales Smoothed forecast Quarter 1234 Actual sales Smoothed forecast EXPONENTIAL SMOOTHING FORECASTING EXAMPLE
Y = X Figure SMR2-3 Fitting a Trend Regression to Seasonally Adjusted Sales Data Sales Time Period
Actual sales Seasonally adjusted sales Two-period moving average forecast seasonally corrected Three-period moving average forecast seasonally corrected Two-period moving average forecastThree-period moving average forecast F 3 = ( S 1 + S 2 ) x I 3 F 4 = ( S 1 + S 2 + S 3 ) x I = ( ) x 1.16 = ( ) x = 78.3 = 68.9 Time Periods FORECASTING WITH MOVING AVERAGES