Show simple item record

dc.contributor.authorWellens, Arnoud P.
dc.contributor.authorUdenio, Maxi
dc.contributor.authorBoute, Robert
dc.date.accessioned2021-10-05T13:40:42Z
dc.date.available2021-10-05T13:40:42Z
dc.date.issued2022en_US
dc.identifier.issn0169-2070
dc.identifier.doi10.1016/j.ijforecast.2021.09.011
dc.identifier.urihttp://hdl.handle.net/20.500.12127/6974
dc.description.abstractThe winning machine learning methods of the M5 Accuracy competition demonstrated high levels of forecast accuracy compared to the top-performing benchmarks in the history of the Mcompetitions. Yet, large-scale adoption is hampered due to the signi cant computational requirements to model, tune, and train these state-of-the-art algorithms. To overcome this major issue, we discuss the potential of transfer learning (TL) to reduce the computational e ort in hierarchical forecasting and provide proof of concept that TL can be applied on M5 top-performing methods. We demonstrate our easy-to-use TL framework on the recursive store level LightGBM models of the M5 winning method and attain similar levels of forecast accuracy with roughly 25% less training time. Our ndings provide evidence for a novel application of TL to facilitate practical applicability of the M5 winning methods in large-scale settings with hierarchically structured data.en_US
dc.language.isoenen_US
dc.publisherElsevieren_US
dc.subjectM5 Accuracy Competitionen_US
dc.subjectComputational Requirementsen_US
dc.subjectTransfer Learningen_US
dc.subjectLightGBMen_US
dc.subjectHierarchical Forecastingen_US
dc.titleTransfer learning for hierarchical forecasting: Reducing computational efforts of M5 winning methoden_US
dc.identifier.journalInternational Journal of Forecastingen_US
dc.source.volume38
dc.source.issue4
dc.source.beginpage1482
dc.source.endpage1491
dc.contributor.departmentKU Leuven, Research Center for Operations Management, Naamsestraat 69, Leuven, 3000, Belgiumen_US
vlerick.knowledgedomainOperations & Supply Chain Managementen_US
vlerick.typearticleJournal article with impact factoren_US
vlerick.vlerickdepartmentTOMen_US
dc.identifier.vperid102358en_US


Files in this item

Thumbnail
Name:
Publisher version

This item appears in the following Collection(s)

Show simple item record