11. demand forecasting 3 gp
Download as PPT, PDF0 likes78 views
This document discusses demand forecasting techniques. It begins with an introduction to forecasting and its uses in marketing and production planning. It then covers characteristics of forecasts and different forecasting horizons. The rest of the document discusses and provides examples of various forecasting techniques including judgmental methods, time series methods, causal methods, qualitative techniques like the Delphi method, and quantitative techniques like moving averages and exponential smoothing. It also covers evaluating and improving forecasts over time.
11. demand forecasting 3 gp
- 1. Demand Forecasting Professor & Lawyer. Puttu Guru Prasad, M.Com. M.B.A., L.L.B., M.Phil, PGDFTM, APSET. ICFAI TMF, (PhD) at JNTUK, Expert Resource person at APHRDI, Bapatla, Senior Faculty for Management Studies, Certified NSS Program Officer, Coordinator – College Beautification S&H Department, VVIT, Nambur, 93 94 96 98 98, 807 444 95 39,
- 3. Forecasting Marketing: forecasts sales for new and existing products. Production: uses sales forecasts to plan production and operations; sometimes involved in generating sales forecasts.
- 4. Characteristics of Forecasts They are usually wrong A good forecast is usually more than a single number Aggregate forecast are more accurate The longer the forecasting horizon, the less accurate the forecasts will be Forecasts should not be used to the exclusion of known information
- 5. Forecasting Horizon Short term (inventory management, production plans..) Intermediate term (sales patterns for product families..) Long term (long term planning of capacity needs)
- 6. Forecasting Techniques Judgmental Models Time Series Methods Causal Methods Forecasting Technique Delphi Method Moving Average Exponential Smoothing Regression Analysis Seasonality Models
- 7. Types of forecasting Methods Subjective methods Sales force composites Customer survey Jury of executive opinion The Delphi method Objective methods Causal methods Time series methods
- 8. Qualitative Methods Don’t have data Don’t have time to develop a forecast Often used in practice “Close enough” Depend on expert opinions Market surveys More appropriate for long term forecasts
- 9. Delphi Technique A method to obtain a consensus forecast by using opinions from a group of “experts” expert opinion consulting salespersons consulting consumers
- 10. Causal Methods Causal methods use data from sources other than the series being predicted. If Y is the phenomenon to be forecast and X1 , X2 , . .., Xn are the n variables we believe to be related to Y, then a causal model is one in which the forecast for Y is some function of these variables: Y = f (X1 , X2 , . .., Xn ) Econometric models are causal models in which the relationship between Y and (X1 , X2 , . .., Xn ) is linear. That is Y = ao + a1 X1 + a2 X2 + … an Xn for some constants a1 , a2 , . . . , an
- 11. Forecasting Steps for Quantitative Methods Collect data Reduce/clean data Build and evaluate model(s) Forecast (model extrapolation) Track the forecast
- 12. Identify the correct pattern • Collect data. Look for possible cause/effect relationships • Determine which form can be used to generate the pattern • Determine specific values of the parameters
- 14. Building Models Plot data over time. (remove outliers & get right scale). Using part of the data, estimate model parameters. Forecast the rest of the data with the model. Evaluate accuracy of the model. Use judgment to modify. Keep track of model accuracy over time (redo, if needed).
- 16. Time series Analysis Patterns that arise most often Trend Seasonality Cycles Randomness
- 17. Time Series Patterns Fig. 2-2
- 18. Notation : Observed value of the demand during period t time series we would like to predict forecast made for period t in period t-1 forecast made at the end of t-1 after having observed , , …1−tD : :}1,{ t t t F tD D ≥ 2−tD
- 19. Time Series Forecast For some set of weights ,...., 10 0 aa DaF n ntnt ∑ ∞ = −=
- 20. Evaluating forecasts Forecast error in period t For multiple-step-ahead ttt DFe −= ttt DFe −= −τ
- 21. Evaluating Forecasts Mean Absolute Deviation Mean Square Error n e MAD n i i∑= = 1 || n e MSE n i i∑= = 1 2
- 22. Forecast Errors Over Time Fig. 2-3
- 23. TIME SERIES METHODS Stationary Series A stationary time series is represented by a constant plus a random fluctuation: Dt = µ+ εt where µ is an unknown constant corresponding to the mean of the series and εt is a random error with mean 0 and variance σ2 . The methods described for stationary series are: Moving Averages Exponential Smoothing
- 24. Methods of Forecasting Stationary Series Moving Averages Exponential Smoothing N DDD N D F Nttt t Nti i t −−− − −= +++ == ∑ ...21 1 11 )1( −− −+= ttt FDF αα
- 25. Moving Average N DDD F Nttt t −−− +++ = ...21
- 26. Month Deliveries Jan 120 Feb 90 Mar 100 Apr 75 May 110 Jun 50 Jul 75 Aug 130 Sep 110 Oct 90 0 20 40 60 80 100 120 140 Jan Feb Mar Apr May Jun Jul Aug Sep Oct Mont h
- 27. Month Deliveries MA(3) MA(6) Jan 120 Feb 90 Mar 100 Apr 75 103 May 110 88 Jun 50 95 Jul 75 78 91 Aug 130 78 83 Sep 110 85 90 Oct 90 105 92 110 94
- 28. 0 20 40 60 80 100 120 140 1 2 3 4 5 6 7 8 9 10 11
- 29. Month Deliveries MA(3) MA(6) 1 2 2 4 3 6 4 8 4 5 10 6 6 12 8 7 14 10 7 8 16 12 9 9 18 14 11 10 20 16 13 11 22 18 15 12 24 20 17 22 19
- 30. Moving-Average Forecasts Lag Behind a Trend Fig. 2-4
- 31. EXPONENTIAL SMOOTHING Current forecast is a weighted average of the last forecast and the current value of demand New forecast = α (current observation of demand) + (1- α ) (last forecast)
- 32. Exponential Smoothing 11 111 11 )( )1( −− −−− −− −= −−= −+= ttt tttt ttt eFF DFFF FDF α α αα Ft = Ft-1 – (fraction of the observed forecast error in t-1) If we forecast high in period t-1 error is positive adjustment to decrease current forecast If we forecast low in period t-1 error is negative adjustment to increase current forecast
- 33. ( ) 1 2 2 21 221 11 1 )1()1( )1( )1( −− ∞ = −−− −−− −− ∑ −= −+−+= −+= −+= it oi i t tttt ttt ttt DF FDDF FDF FDF αα αααα αα αα
- 34. Example Quarter Failures Forecast 1 200 200 2 250 200 3 175 205 4 186 202 5 225 201 6 285 203 7 305 211 8 190 220
- 35. 0 50 100 150 200 250 300 350 1 2 3 4 5 6 7 8
- 37. Exponential Smoothing for Different Values of Alpha Fig. 2-6
- 38. Smaller values of α produce more stable forecasts, whereas larger values of α will produce forecasts which react more quickly to changes in the demand pattern.
- 39. Comparison 2 1)1( )...321( 1 + = + =++++ N N NN N N ( ) α αα 1 1 1 1 =− − ∞ = ∑ i i i 2 11 + = N α
- 40. Similarities & Differences Stationary series Single parameter Lag behind a trend When α=2/(N+1) Same distribution of forecast error ES weighted average of all past data MA only last N periods MA : save past N data ES : only last forecast
- 41. Multiple-Step-Ahead Forecasts Same as one-step-ahead-forecast
- 42. Trend Based Methods Regression Analysis Double Exponential Smoothing btaFt += tttt GSF ττ +=+,
- 43. Double Exponential Smoothing Intercept at time t and slope at time t ))(1( 11 −− +−+= tttt GSDS αα 11 )1()( −− −+−= tttt GSSG ββ tttt GSF ττ +=+,