improved supply chain management based on hybrid demand forecasts

《improved supply chain management based on hybrid demand forecasts》由会员上传分享，免费在线阅读，更多相关内容在工程资料-天天文库。

1、Int.J.ProductionEconomics143(2013)198–206ContentslistsavailableatSciVerseScienceDirectInt.J.ProductionEconomicsjournalhomepage:www.elsevier.com/locate/ijpeIntermittentdemandforecastswithneuralnetworksnNikolaosKourentzesDepartmentofManagementScience,LancasterUniversity

2、ManagementSchool,Lancaster,LancashireLA14YX,UKarticleinfoabstractArticlehistory:Intermittentdemandappearswhendemandeventsoccuronlysporadically.TypicallysuchtimeseriesReceived24February2012havefewobservationsmakingintermittentdemandforecastingchallenging.Forecasterrors

3、canbeAccepted9January2013costlyintermsofunmetdemandorobsolescentstock.IntermittentdemandforecastinghasbeenAvailableonline20January2013addressedusingestablishedforecastingmethods,includingsimplemovingaverages,exponentialKeywords:smoothingandCroston’smethodwithitsvarian

4、ts.Thisstudyproposesaneuralnetwork(NN)Intermittentdemandmethodologytoforecastintermittenttimeseries.TheseNNsareusedtoprovidedynamicdemandNeuralnetworksrateforecasts,whichdonotassumeconstantdemandrateinthefutureandcancaptureinteractionsCroston’smethodbetweenthenon-zero

5、demandandtheinter-arrivalrateofdemandevents.ThisovercomestheForecastinglimitationsofCroston’smethod.Inordertomitigatetheissueoflimitedfittingsample,whichisSlowmovingitemscommoninintermittentdemand,theproposedmodelsuseregularisedtrainingandmedianensemblesovermultipletra

6、ininginitialisationstoproducerobustforecasts.TheNNsareevaluatedagainstestablishedbenchmarksusingbothforecastingaccuracyandinventorymetrics.Thefindingsofforecastingandinventorymetricsareconflicting.WhileNNsachievedpoorforecastingaccuracyandbias,allNNvariantsachievedhighe

7、rservicelevelsthanthebestperformingCroston’smethodvariant,withoutrequiringanalogousincreasesinstockholdingvolume.Therefore,NNsarefoundtobeeffectiveforintermittentdemandapplications.Thisstudyprovidesfurtherargumentsandevidenceagainsttheuseofconventionalforecastingaccur

8、acymetricstoevaluateforecastingmethodsforintermittentdemand,concludingthatattentiontoinventorymetricsisdesirable.&2013Elsevi