Quản trị kinh doanh - Chapter 12: Forecasting

Chapter 12ForecastingLecture OutlineStrategic Role of Forecasting in Supply Chain Management Components of Forecasting DemandTime Series MethodsForecast AccuracyTime Series Forecasting Using ExcelRegression MethodsCopyright 2011 John Wiley & Sons, Inc.12-2ForecastingPredicting the futureQualitative forecast methodssubjectiveQuantitative forecast methodsbased on mathematical formulasCopyright 2011 John Wiley & Sons, Inc.12-3Supply Chain ManagementAccurate forecasting determines inventory levels in the supply chainContinuous replenishmentsupplier & customer share continuously updated datatypically managed by the supplierreduces inventory for the companyspeeds customer deliveryVariations of continuous replenishmentquick responseJIT (just-in-time)VMI (vendor-managed inventory)stockless inventoryCopyright 2011 John Wiley & Sons, Inc.12-4The Effect of Inaccurate ForecastingCopyright 2011 John Wiley & Sons, Inc.12-5ForecastingQuality ManagementAccurately forecasting customer demand is a key to providing good quality serviceStrategic PlanningSuccessful strategic planning requires accurate forecasts of future products and marketsCopyright 2011 John Wiley & Sons, Inc.12-6Types of Forecasting MethodsDepend ontime framedemand behaviorcauses of behaviorCopyright 2011 John Wiley & Sons, Inc.12-7Time FrameIndicates how far into the future is forecastShort- to mid-range forecasttypically encompasses the immediate futuredaily up to two yearsLong-range forecastusually encompasses a period of time longer than two yearsCopyright 2011 John Wiley & Sons, Inc.12-8Demand BehaviorTrenda gradual, long-term up or down movement of demandRandom variationsmovements in demand that do not follow a patternCyclean up-and-down repetitive movement in demandSeasonal patternan up-and-down repetitive movement in demand occurring periodicallyCopyright 2011 John Wiley & Sons, Inc.12-9Forms of Forecast MovementCopyright 2011 John Wiley & Sons, Inc.12-10Time(a) TrendTime(d) Trend with seasonal patternTime(c) Seasonal patternTime(b) CycleDemandDemandDemandDemandRandom movementForecasting MethodsTime seriesstatistical techniques that use historical demand data to predict future demandRegression methodsattempt to develop a mathematical relationship between demand and factors that cause its behaviorQualitativeuse management judgment, expertise, and opinion to predict future demandCopyright 2011 John Wiley & Sons, Inc.12-11Qualitative MethodsManagement, marketing, purchasing, and engineering are sources for internal qualitative forecastsDelphi methodinvolves soliciting forecasts about technological advances from expertsCopyright 2011 John Wiley & Sons, Inc.12-12Forecasting ProcessCopyright 2011 John Wiley & Sons, Inc.12-136. Check forecast accuracy with one or more measures4. Select a forecast model that seems appropriate for data5. Develop/compute forecast for period of historical data8a. Forecast over planning horizon9. Adjust forecast based on additional qualitative information and insight10. Monitor results and measure forecast accuracy8b. Select new forecast model or adjust parameters of existing model7.Is accuracy of forecast acceptable?1. Identify the purpose of forecast3. Plot data and identify patterns 2. Collect historical dataNoYesTime SeriesAssume that what has occurred in the past will continue to occur in the futureRelate the forecast to only one factor - timeIncludemoving averageexponential smoothinglinear trend lineCopyright 2011 John Wiley & Sons, Inc.12-14Moving AverageNaive forecastdemand in current period is used as next period’s forecastSimple moving averageuses average demand for a fixed sequence of periodsstable demand with no pronounced behavioral patternsWeighted moving averageweights are assigned to most recent dataCopyright 2011 John Wiley & Sons, Inc.12-15Moving Average: Naïve ApproachCopyright 2011 John Wiley & Sons, Inc.12-16Jan 120 Feb 90 Mar 100 Apr 75 May 110 June 50 July 75 Aug 130 Sept 110 Oct 90 ORDERS MONTH PER MONTH -1209010075110507513011090Nov -FORECASTSimple Moving Average Copyright 2011 John Wiley & Sons, Inc.12-17MAn = ni = 1Dinwheren = number of periods in the moving averageDi = demand in period i3-month Simple Moving AverageCopyright 2011 John Wiley & Sons, Inc.12-18Jan 120 Feb 90 Mar 100 Apr 75 May 110 June 50 July 75 Aug 130 Sept 110 Oct 90Nov - ORDERS MONTH PER MONTH MA3 = 3i = 1Di3=90 + 110 + 1303= 110 orders for Nov–––103.388.395.078.378.385.0105.0110.0MOVING AVERAGE5-month Simple Moving AverageCopyright 2011 John Wiley & Sons, Inc.12-19MA5 = 5i = 1Di5=90 + 110 + 130+75+505= 91 orders for NovJan 120 Feb 90 Mar 100 Apr 75 May 110 June 50 July 75 Aug 130 Sept 110 Oct 90Nov - ORDERS MONTH PER MONTH ––– –– 99.085.082.088.095.091.0MOVING AVERAGESmoothing EffectsCopyright 2011 John Wiley & Sons, Inc.12-20150 –125 –100 –75 –50 –25 –0 – | | | | | | | | | | | Jan Feb Mar Apr May June July Aug Sept Oct NovActualOrdersMonth5-month3-monthWeighted Moving AverageCopyright 2011 John Wiley & Sons, Inc.12-21Adjusts moving average method to more closely reflect data fluctuationsWMAn = i = 1Wi DiwhereWi = the weight for period i, between 0 and 100 percent Wi = 1.00nWeighted Moving Average ExampleCopyright 2011 John Wiley & Sons, Inc.12-22MONTH WEIGHT DATAAugust 17% 130September 33% 110October 50% 90WMA3 = 3i = 1Wi Di= (0.50)(90) + (0.33)(110) + (0.17)(130)= 103.4 ordersNovember ForecastExponential SmoothingCopyright 2011 John Wiley & Sons, Inc.12-23Averaging method Weights most recent data more stronglyReacts more to recent changesWidely used, accurate methodExponential SmoothingCopyright 2011 John Wiley & Sons, Inc.12-24Ft +1 = Dt + (1 - )Ftwhere: Ft +1 = forecast for next period Dt = actual demand for present period Ft = previously determined forecast for present period = weighting factor, smoothing constant0.0  1.0If = 0.20, then Ft +1 = 0.20Dt + 0.80 FtIf = 0, then Ft +1 = 0Dt + 1 Ft = Ft Forecast does not reflect recent dataIf = 1, then Ft +1 = 1Dt + 0 Ft =Dt Forecast based only on most recent dataEffect of Smoothing ConstantCopyright 2011 John Wiley & Sons, Inc.12-25Exponential Smoothing (α=0.30)Copyright 2011 John Wiley & Sons, Inc.12-26F2 = D1 + (1 - )F1 = (0.30)(37) + (0.70)(37) = 37F3 = D2 + (1 - )F2 = (0.30)(40) + (0.70)(37) = 37.9F13 = D12 + (1 - )F12 = (0.30)(54) + (0.70)(50.84) = 51.79 PERIOD MONTH DEMAND 1 Jan 37 2 Feb 40 3 Mar 41 4 Apr 37 5 May 45 6 Jun 50 7 Jul 43 8 Aug 47 9 Sep 56 10 Oct 52 11 Nov 55 12 Dec 54 Exponential SmoothingCopyright 2011 John Wiley & Sons, Inc.12-27 FORECAST, Ft + 1 PERIOD MONTH DEMAND ( = 0.3) ( = 0.5) 1 Jan 37 – – 2 Feb 40 37.00 37.00 3 Mar 41 37.90 38.50 4 Apr 37 38.83 39.75 5 May 45 38.28 38.37 6 Jun 50 40.29 41.68 7 Jul 43 43.20 45.84 8 Aug 47 43.14 44.42 9 Sep 56 44.30 45.71 10 Oct 52 47.81 50.85 11 Nov 55 49.06 51.42 12 Dec 54 50.84 53.21 13 Jan – 51.79 53.61Exponential SmoothingCopyright 2011 John Wiley & Sons, Inc.12-2870 –60 –50 –40 –30 –20 –10 –0 – | | | | | | | | | | | | | 1 2 3 4 5 6 7 8 9 10 11 12 13ActualOrdersMonth = 0.50 = 0.30Adjusted Exponential SmoothingCopyright 2011 John Wiley & Sons, Inc.12-29AFt +1 = Ft +1 + Tt +1where T = an exponentially smoothed trend factorTt +1 = (Ft +1 - Ft) + (1 - ) Ttwhere Tt = the last period trend factor = a smoothing constant for trend 0 ≤  ≤ 1 Adjusted Exponential Smoothing (β=0.30)Copyright 2011 John Wiley & Sons, Inc.12-30 PERIOD MONTH DEMAND 1 Jan 37 2 Feb 40 3 Mar 41 4 Apr 37 5 May 45 6 Jun 50 7 Jul 43 8 Aug 47 9 Sep 56 10 Oct 52 11 Nov 55 12 Dec 54 T3 = (F3 - F2) + (1 - ) T2 = (0.30)(38.5 - 37.0) + (0.70)(0) = 0.45AF3 = F3 + T3 = 38.5 + 0.45 = 38.95T13 = (F13 - F12) + (1 - ) T12 = (0.30)(53.61 - 53.21) + (0.70)(1.77) = 1.36AF13 = F13 + T13 = 53.61 + 1.36 = 54.97Adjusted Exponential SmoothingCopyright 2011 John Wiley & Sons, Inc.12-31 FORECAST TREND ADJUSTED PERIOD MONTH DEMAND Ft +1 Tt +1 FORECAST AFt +1 1 Jan 37 37.00 – – 2 Feb 40 37.00 0.00 37.00 3 Mar 41 38.50 0.45 38.95 4 Apr 37 39.75 0.69 40.44 5 May 45 38.37 0.07 38.44 6 Jun 50 38.37 0.07 38.44 7 Jul 43 45.84 1.97 47.82 8 Aug 47 44.42 0.95 45.37 9 Sep 56 45.71 1.05 46.76 10 Oct 52 50.85 2.28 58.13 11 Nov 55 51.42 1.76 53.19 12 Dec 54 53.21 1.77 54.98 13 Jan – 53.61 1.36 54.96Adjusted Exponential SmoothingForecastsCopyright 2011 John Wiley & Sons, Inc.12-3270 –60 –50 –40 –30 –20 –10 –0 – | | | | | | | | | | | | | 1 2 3 4 5 6 7 8 9 10 11 12 13ActualDemandPeriodForecast ( = 0.50)Adjusted forecast ( = 0.30)Linear Trend LineCopyright 2011 John Wiley & Sons, Inc.12-33y = a + bx wherea = interceptb = slope of the linex = time periody = forecast for demand for period x b = a = y - b x where n = number of periods x = = mean of the x values y = = mean of the y values xy - nxyx2 - nx2xnynLeast Squares ExampleCopyright 2011 John Wiley & Sons, Inc.12-34x(PERIOD) y(DEMAND) xy x2 1 73 37 1 2 40 80 4 3 41 123 9 4 37 148 16 5 45 225 25 6 50 300 36 7 43 301 49 8 47 376 64 9 56 504 81 10 52 520 100 11 55 605 121 12 54 648 144 78 557 3867 650Least Squares ExampleCopyright 2011 John Wiley & Sons, Inc.12-35x = = 6.5y = = 46.42b = = =1.72a = y - bx = 46.42 - (1.72)(6.5) = 35.23867 - (12)(6.5)(46.42)650 - 12(6.5)2xy - nxyx2 - nx2781255712Copyright 2011 John Wiley & Sons, Inc.12-36Linear trend liney = 35.2 + 1.72xForecast for period 13y = 35.2 + 1.72(13) = 57.56 units70 –60 –50 –40 –30 –20 –10 – | | | | | | | | | | | | | 1 2 3 4 5 6 7 8 9 10 11 12 13ActualDemandPeriodLinear trend lineSeasonal AdjustmentsCopyright 2011 John Wiley & Sons, Inc.12-37Repetitive increase/ decrease in demandUse seasonal factor to adjust forecastSeasonal factor = Si =DiDSeasonal AdjustmentCopyright 2011 John Wiley & Sons, Inc.12-382002 12.6 8.6 6.3 17.5 45.02003 14.1 10.3 7.5 18.2 50.12004 15.3 10.6 8.1 19.6 53.6Total 42.0 29.5 21.9 55.3 148.7 DEMAND (1000’S PER QUARTER)YEAR 1 2 3 4 TotalS1 = = = 0.28 D1D42.0148.7S2 = = = 0.20 D2D29.5148.7S4 = = = 0.37 D4D55.3148.7S3 = = = 0.15 D3D21.9148.7Seasonal AdjustmentCopyright 2011 John Wiley & Sons, Inc.12-39SF1 = (S1) (F5) = (0.28)(58.17) = 16.28 SF2 = (S2) (F5) = (0.20)(58.17) = 11.63SF3 = (S3) (F5) = (0.15)(58.17) = 8.73SF4 = (S4) (F5) = (0.37)(58.17) = 21.53y = 40.97 + 4.30x = 40.97 + 4.30(4) = 58.17For 2005Forecast AccuracyForecast errordifference between forecast and actual demandMADmean absolute deviationMAPDmean absolute percent deviationCumulative errorAverage error or biasCopyright 2011 John Wiley & Sons, Inc.12-40Mean Absolute Deviation (MAD)Copyright 2011 John Wiley & Sons, Inc.12-41where t = period number Dt = demand in period t Ft = forecast for period t n = total number of periods  = absolute value Dt - Ft nMAD =Copyright 2011 John Wiley & Sons, Inc.12-42MAD Example 1 37 37.00 – – 2 40 37.00 3.00 3.00 3 41 37.90 3.10 3.10 4 37 38.83 -1.83 1.83 5 45 38.28 6.72 6.72 6 50 40.29 9.69 9.69 7 43 43.20 -0.20 0.20 8 47 43.14 3.86 3.86 9 56 44.30 11.70 11.70 10 52 47.81 4.19 4.19 11 55 49.06 5.94 5.94 12 54 50.84 3.15 3.15 557 49.31 53.39PERIOD DEMAND, Dt Ft ( =0.3) (Dt - Ft) |Dt - Ft|MAD CalculationCopyright 2011 John Wiley & Sons, Inc.12-43 Dt - Ft nMAD = = = 4.8553.3911Other Accuracy MeasuresCopyright 2011 John Wiley & Sons, Inc.12-44Mean absolute percent deviation (MAPD)MAPD =|Dt - Ft|DtCumulative errorE = etAverage errorE =etnComparison of ForecastsCopyright 2011 John Wiley & Sons, Inc.12-45FORECAST MAD MAPD E (E)Exponential smoothing (= 0.30) 4.85 9.6% 49.31 4.48Exponential smoothing (= 0.50) 4.04 8.5% 33.21 3.02Adjusted exponential smoothing 3.81 7.5% 21.14 1.92 (= 0.50, = 0.30)Linear trend line 2.29 4.9% – –Forecast ControlTracking signalmonitors the forecast to see if it is biased high or low1 MAD ≈ 0.8 бControl limits of 2 to 5 MADs are used most frequentlyCopyright 2011 John Wiley & Sons, Inc.12-46Tracking signal = =(Dt - Ft)MADEMADTracking Signal ValuesCopyright 2011 John Wiley & Sons, Inc.12-47 1 37 37.00 – – – 2 40 37.00 3.00 3.00 3.00 3 41 37.90 3.10 6.10 3.05 4 37 38.83 -1.83 4.27 2.64 5 45 38.28 6.72 10.99 3.66 6 50 40.29 9.69 20.68 4.87 7 43 43.20 -0.20 20.48 4.09 8 47 43.14 3.86 24.34 4.06 9 56 44.30 11.70 36.04 5.01 10 52 47.81 4.19 40.23 4.92 11 55 49.06 5.94 46.17 5.02 12 54 50.84 3.15 49.32 4.85 DEMAND FORECAST, ERROR E = PERIOD Dt Ft Dt - Ft (Dt - Ft) MAD – 1.002.001.623.004.255.016.007.19 8.18 9.20 10.17TRACKINGSIGNALTS3 = = 2.006.103.05Tracking Signal PlotCopyright 2011 John Wiley & Sons, Inc.12-483 –2 –1 –0 –-1 –-2 –-3 – | | | | | | | | | | | | | 0 1 2 3 4 5 6 7 8 9 10 11 12Tracking signal (MAD)PeriodExponential smoothing ( = 0.30)Linear trend lineStatistical Control ChartsCopyright 2011 John Wiley & Sons, Inc.12-49 =(Dt - Ft)2n - 1Using  we can calculate statistical control limits for the forecast errorControl limits are typically set at  3Statistical Control ChartsCopyright 2011 John Wiley & Sons, Inc.12-50Errors18.39 –12.24 –6.12 –0 –-6.12 –-12.24 –-18.39 – | | | | | | | | | | | | | 0 1 2 3 4 5 6 7 8 9 10 11 12PeriodUCL = +3LCL = -3Time Series Forecasting Using ExcelExcel can be used to develop forecasts:Moving averageExponential smoothingAdjusted exponential smoothingLinear trend lineCopyright 2011 John Wiley & Sons, Inc.12-51Exponentially Smoothed and Adjusted Exponentially Smoothed ForecastsCopyright 2011 John Wiley & Sons, Inc.12-52=B5*(C11-C10)+(1-B5)*D10=C10+D10=ABS(B10-E10)=SUM(F10:F20)=G22/11Demand and Exponentially Smoothed ForecastCopyright 2011 John Wiley & Sons, Inc.12-53Click on “Insert” then “Line”Data Analysis OptionCopyright 2011 John Wiley & Sons, Inc.12-54Forecasting With Seasonal AdjustmentCopyright 2011 John Wiley & Sons, Inc.12-55Forecasting With OM Tools Copyright 2011 John Wiley & Sons, Inc.12-56Regression MethodsLinear regressionmathematical technique that relates a dependent variable to an independent variable in the form of a linear equationCorrelationa measure of the strength of the relationship between independent and dependent variablesCopyright 2011 John Wiley & Sons, Inc.12-57Linear RegressionCopyright 2011 John Wiley & Sons, Inc.12-58y = a + bx a = y - b x b =where a = intercept b = slope of the line x = = mean of the x data y = = mean of the y data xy - nxyx2 - nx2xnynLinear Regression ExampleCopyright 2011 John Wiley & Sons, Inc.12-59 x y (WINS) (ATTENDANCE) xy x2 4 36.3 145.2 16 6 40.1 240.6 36 6 41.2 247.2 36 8 53.0 424.0 64 6 44.0 264.0 36 7 45.6 319.2 49 5 39.0 195.0 25 7 47.5 332.5 49 49 346.7 2167.7 311Linear Regression ExampleCopyright 2011 John Wiley & Sons, Inc.12-60 x = = 6.125 y = = 43.36 b = = = 4.06 a = y - bx = 43.36 - (4.06)(6.125) = 18.46498346.98xy - nxy2x2 - nx2(2,167.7) - (8)(6.125)(43.36)(311) - (8)(6.125)2Linear Regression ExampleCopyright 2011 John Wiley & Sons, Inc.12-61 | | | | | | | | | | | 0 1 2 3 4 5 6 7 8 9 1060,000 –50,000 –40,000 –30,000 –20,000 –10,000 –Linear regression line, y = 18.46 + 4.06xWins, xAttendance, y y = 18.46 + 4.06(7) = 46.88, or 46,880 Attendance forecast for 7 winsCorrelation and Coefficient of DeterminationCorrelation, rMeasure of strength of relationshipVaries between -1.00 and +1.00Coefficient of determination, r2Percentage of variation in dependent variable resulting from changes in the independent variableCopyright 2011 John Wiley & Sons, Inc.12-62n xy -  x y[n x2 - ( x)2] [n y2 - ( y)2]r =Coefficient of determination r2 = (0.947)2 = 0.897r =(8)(2,167.7) - (49)(346.9)[(8)(311) - (49)2] [(8)(15,224.7) - (346.9)2]r = 0.947Computing CorrelationCopyright 2011 John Wiley & Sons, Inc.12-63Regression Analysis With ExcelCopyright 2011 John Wiley & Sons, Inc.12-64=INTERCEPT(B5:B12,A5:A12)=CORREL(B5:B12,A5:A12)=SUM(B5:B12)Regression Analysis with ExcelCopyright 2011 John Wiley & Sons, Inc.12-65Regression Analysis With ExcelCopyright 2011 John Wiley & Sons, Inc.12-66Multiple RegressionCopyright 2011 John Wiley & Sons, Inc.12-67Study the relationship of demand to two or more independent variablesy = 0 + 1x1 + 2x2 + kxkwhere 0 = the intercept 1, , k = parameters for the independent variables x1, , xk = independent variablesMultiple Regression With ExcelCopyright 2011 John Wiley & Sons, Inc.12-68r2, the coefficientof determinationRegression equationcoefficients for x1 and x2Multiple Regression ExampleCopyright 2011 John Wiley & Sons, Inc.12-69y = 19,094.42 + 3560.99 x1 + .0368 x2y = 19,094.42 + 3560.99 (7) + .0368 (60,000) = 46,229.35Copyright 2011 John Wiley & Sons, Inc.12-70Copyright 2011 John Wiley & Sons, Inc.All rights reserved. Reproduction or translation of this work beyond that permitted in section 117 of the 1976 United States Copyright Act without express permission of the copyright owner is unlawful. Request for further information should be addressed to the Permission Department, John Wiley & Sons, Inc. The purchaser may make back-up copies for his/her own use only and not for distribution or resale. The Publisher assumes no responsibility for errors, omissions, or damages caused by the use of these programs or from the use of the information herein.