Optimizing inventory control through a data-driven and model-independent framework

Θεοδώρου, Ευάγγελος

dc.contributor.author	Θεοδώρου, Ευάγγελος
dc.date.accessioned	2023-04-28T09:03:30Z
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/57580
dc.identifier.uri	http://dx.doi.org/10.26240/heal.ntua.25277
dc.rights	Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα	*
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/3.0/gr/	*
dc.subject	Inventory control management	en
dc.subject	Machine learning	en
dc.subject	Demand patterns	en
dc.subject	Large scale optimization	en
dc.title	Optimizing inventory control through a data-driven and model-independent framework	en
heal.type	journalArticle
heal.classification	Επιχειρησιακή έρευνα	el
heal.classification	Operational research	en
heal.contributorName	Σπηλιώτης, Ευαγγελος
heal.contributorName	Ασημακόπουλος, Βασίλειος
heal.dateAvailable	2024-04-27T21:00:00Z
heal.language	en
heal.access	embargo
heal.recordProvider	ntua	el
heal.publicationDate	2022-12-27
heal.bibliographicCitation	Theodorou, E., Spiliotis, E., & Assimakopoulos, V., Optimizing inventory control through a data-driven and model-independent framework, EURO Journal on Transportation and Logistics, 12, 100103, Elsevier, 2022.	en
heal.abstract	Machine learning has shown great potential in various domains, but its appearance in inventory control optimization settings remains rather limited. We propose a novel inventory cost minimization framework that exploits advanced decision-tree based models to approximate inventory performance at an item level, considering demand patterns and key replenishment policy parameters as input. The suggested approach enables data-driven approximations that are faster to perform compared to standard inventory simulations, while being flexible in terms of the methods used for forecasting demand or estimating inventory level, lost sales, and number of orders, among others. Moreover, such approximations can be based on knowledge extracted from different sets of items than the ones being optimized, thus providing more accurate proposals in cases where historical data are scarce or highly affected by stock-outs. The framework was evaluated using part of the M5 competition’s data. Our results suggest that the proposed framework, and especially its transfer learning variant, can result in significant improvements, both in terms of total inventory cost and realized service level.	en
heal.publisher	Elsevier	en
heal.journalName	EURO Journal on Transportation and Logistics	en
heal.journalType	peer-reviewed
heal.fullTextAvailability	false
dc.identifier.doi	https://doi.org/10.1016/j.ejtl.2022.100103	el