File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: A Practical End-to-End Inventory Management Model with Deep Learning

TitleA Practical End-to-End Inventory Management Model with Deep Learning
Authors
Keywordsdeep learning
e-commerce
end-to-end decision-making
inventory management
Issue Date1-Feb-2023
PublisherInstitute for Operations Research and Management Sciences
Citation
Management Science, 2023, v. 69, n. 2, p. 759-773 How to Cite?
AbstractWe investigate a data-driven multiperiod inventory replenishment problem with uncertain demand and vendor lead time (VLT) with accessibility to a large quantity of historical data. Different from the traditional two-step predict-then-optimize (PTO) solution framework, we propose a one-step end-to-end (E2E) framework that uses deep learning models to output the suggested replenishment amount directly from input features without any intermediate step. The E2E model is trained to capture the behavior of the optimal dynamic programming solution under historical observations without any prior assumptions on the distributions of the demand and the VLT. By conducting a series of thorough numerical experiments using real data from one of the leading e-commerce companies, we demonstrate the advantages of the proposed E2E model over conventional PTO frameworks. We also conduct a field experiment with JD.com, and the results show that our new algorithm reduces holding cost, stockout cost, total inventory cost, and turnover rate substantially compared with JD's current practice. For the supply chain management industry, our E2E model shortens the decision process and provides an automatic inventory management solution with the possibility to generalize and scale. The concept of E2E, which uses the input information directly for the ultimate goal, can also be useful in practice for other supply chain management circumstances.
Persistent Identifierhttp://hdl.handle.net/10722/336537
ISSN
2023 Impact Factor: 4.6
2023 SCImago Journal Rankings: 5.438
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorQi, M-
dc.contributor.authorShi, Y-
dc.contributor.authorQi, Y-
dc.contributor.authorMa, C-
dc.contributor.authorYuan, R-
dc.contributor.authorWu, D-
dc.contributor.authorShen, ZJ-
dc.date.accessioned2024-02-16T03:57:33Z-
dc.date.available2024-02-16T03:57:33Z-
dc.date.issued2023-02-01-
dc.identifier.citationManagement Science, 2023, v. 69, n. 2, p. 759-773-
dc.identifier.issn0025-1909-
dc.identifier.urihttp://hdl.handle.net/10722/336537-
dc.description.abstractWe investigate a data-driven multiperiod inventory replenishment problem with uncertain demand and vendor lead time (VLT) with accessibility to a large quantity of historical data. Different from the traditional two-step predict-then-optimize (PTO) solution framework, we propose a one-step end-to-end (E2E) framework that uses deep learning models to output the suggested replenishment amount directly from input features without any intermediate step. The E2E model is trained to capture the behavior of the optimal dynamic programming solution under historical observations without any prior assumptions on the distributions of the demand and the VLT. By conducting a series of thorough numerical experiments using real data from one of the leading e-commerce companies, we demonstrate the advantages of the proposed E2E model over conventional PTO frameworks. We also conduct a field experiment with JD.com, and the results show that our new algorithm reduces holding cost, stockout cost, total inventory cost, and turnover rate substantially compared with JD's current practice. For the supply chain management industry, our E2E model shortens the decision process and provides an automatic inventory management solution with the possibility to generalize and scale. The concept of E2E, which uses the input information directly for the ultimate goal, can also be useful in practice for other supply chain management circumstances.-
dc.languageeng-
dc.publisherInstitute for Operations Research and Management Sciences-
dc.relation.ispartofManagement Science-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.subjectdeep learning-
dc.subjecte-commerce-
dc.subjectend-to-end decision-making-
dc.subjectinventory management-
dc.titleA Practical End-to-End Inventory Management Model with Deep Learning-
dc.typeArticle-
dc.identifier.doi10.1287/mnsc.2022.4564-
dc.identifier.scopuseid_2-s2.0-85149127358-
dc.identifier.volume69-
dc.identifier.issue2-
dc.identifier.spage759-
dc.identifier.epage773-
dc.identifier.eissn1526-5501-
dc.identifier.isiWOS:001132227500003-
dc.identifier.issnl0025-1909-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats