介绍operationmanagement项目管理3

McGraw-Hill/IrwinCopyright©2010byTheMcGraw-HillCompanies,Inc.Allrightsreserved.3Forecasting3-2LearningObjectivesListtheelementsofagoodforecast.Outlinethestepsintheforecastingprocess.Describeatleastthreequalitativeforecastingtechniquesandtheadvantagesanddisadvantagesofeach.Compareandcontrastqualitativeandquantitativeapproachestoforecasting.3-3LearningObjectivesBrieflydescribeaveragingtechniques,trendandseasonaltechniques,andregressionanalysis,andsolvetypicalproblems.Describetwomeasuresofforecastaccuracy.Describetwowaysofevaluatingandcontrollingforecasts.Identifythemajorfactorstoconsiderwhenchoosingaforecastingtechnique.3-4FORECAST:Astatementaboutthefuturevalueofavariableofinterestsuchasdemand.Forecastingisusedtomakeinformeddecisions.Long-rangeShort-range3-5ForecastsForecastsaffectdecisionsandactivitiesthroughoutanorganizationAccounting,financeHumanresourcesMarketingMISOperationsProduct/servicedesign3-6AccountingCost/profitestimatesFinanceCashflowandfundingHumanresourcesHiring/recruiting/trainingMarketingPricing,promotion,strategyMISIT/ISsystems,servicesOperationsSchedules,MRP,workloadsProduct/servicedesignNewproductsandservicesUsesofForecastsIseethatyouwillgetanAthissemester.3-7Assumescausalsystempast==futureForecastsrarelyperfectbecauseofrandomnessForecastsmoreaccurateforgroupsvs.individualsForecastaccuracydecreasesastimehorizonincreasesFeaturesofForecasts3-8ElementsofaGoodForecastTimelyAccurateReliableWritten3-9StepsintheForecastingProcessStep1DeterminepurposeofforecastStep2EstablishatimehorizonStep3SelectaforecastingtechniqueStep4Obtain,cleanandanalyzedataStep5MaketheforecastStep6Monitortheforecast“Theforecast”3-10TypesofForecastsJudgmental:usessubjectiveinputsTimeseries:useshistoricaldata,assumingthefuturewillbelikethepastAssociativemodels:usesexplanatoryvariablestopredictthefuture3-11JudgmentalForecastsExecutiveopinionsSalesforceopinionsConsumersurveysOutsideopinionDelphimethodOpinionsofmanagersandstaffAchievesaconsensusforecast3-12TimeSeriesForecastsTrend:long-termmovementindataSeasonality:short-termregularvariationsindataCycles:wavelikevariationsofmorethanoneyear’sdurationIrregularvariations:causedbyunusualcircumstancesRandomvariations:causedbychance3-13ForecastVariationsTrendIrregularvariationSeasonalvariations908988Figure3.1Cycles3-14NaiveForecastsUh,givemeaminute....Wesold250wheelslastweek....Now,nextweekweshouldsell....Theforecastforanyperiodequalsthepreviousperiod’sactualvalue.3-15SimpletouseVirtuallynocostQuickandeasytoprepareDataanalysisisnonexistentEasilyunderstandableCannotprovidehighaccuracyCanbeastandardforaccuracyNaiveForecasts3-16StabletimeseriesdataF(t)=A(t-1)SeasonalvariationsF(t)=A(t-n)DatawithtrendsF(t)=A(t-1)+(A(t-1)–A(t-2))UsesofNaiveForecasts3-17TechniquesforAveragingMovingaverageWeightedmovingaverageExponentialsmoothing3-18MovingAveragesMovingaverage:Atechniquethataveragesanumberofrecentactualvalues,updatedasnewvaluesbecomeavailable.Weightedmovingaverage:Morerecentvaluesinaseriesaregivenmoreweightincomputingtheforecast.Ft=MAn=nAt-n+…At-2+At-1Ft=WMAn=nwnAt-n+…wn-1At-2+w1At-13-19SimpleMovingAverage35373941434547123456789101112ActualMA3MA5Ft=MAn=nAt-n+…At-2+At-13-20ExponentialSmoothingPremise:Themostrecentobservationsmighthavethehighestpredictivevalue.Therefore,weshouldgivemoreweighttothemorerecenttimeperiodswhenforecasting.Ft=Ft-1+(At-1-Ft-1)3-21ExponentialSmoothingWeightedaveragingmethodbasedonpreviousforecastplusapercentageoftheforecasterrorA-Fistheerrorterm,isthe%feedbackFt=Ft-1+(At-1-Ft-1)3-22PeriodActualAlpha=0.1ErrorAlpha=0.4Error14224042-2.0042-234341.81.2041.21.844041.92-1.9241.92-1.9254141.73-0.7341.15-0.1563941.66-2.6641.09-2.0974641.394.6140.255.7584441.852.1542.551.4594542.072.9343.131.87103842.36-4.3643.88-5.88114041.92-1.9241.53-1.531241.7340.92Example3:ExponentialSmoothing3-23PickingaSmoothingConstant35404550123456789101112PeriodDemand.1.4Actual3-24CommonNonlinearTrendsParabolicExponentialGrowthFigure3.53-25LinearTrendEquationFt=Forecastforperiodtt=Specifiednumberoftimeperiodsa=ValueofFtatt=0b=SlopeofthelineFt=a+bt012345tFt3-26Calculatingaandbb=n(ty)-tynt2-(t)2a=y-btn3-27LinearTrendEquationExampletyWeekt2Salesty111501502415731439162486416166664525177885t=15t2=55y=812ty=2499(t)2=2253-28LinearTrendCalculationy=143.5+6.3ta=812-6.3(15)5=b=5(2499)-15(812)5(55)-225=12495-12180275-225=6.3143.53-29TechniquesforSeasonalitySeasonalvariationsRegularlyrepeatingmovementsinseriesvaluesthatcanbetiedtorecurringeventsSeasonalrelativePercentageofaverageortrendCenteredmovingaverageAmovingaveragepositionedatthecenterofthedatathatwereusedtocomputeit3-30AssociativeForecastingPredictorvariables:usedtopredictvaluesofvariableinterestRegression:techniqueforfittingalinetoasetofpointsLeastsquaresline:minimizessumofsquareddeviationsaroundtheline3-31LinearModelSeemsReasonableAstraightlineisfittedtoasetofsamplepoints.010203040500510152025XY7152106134151425152716241220142720441534717Computedrelationship3-32L