IDEAS home Printed from https://ideas.repec.org/a/inm/ormnsc/v69y2023i2p759-773.html
   My bibliography  Save this article

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

Author

Listed:
  • Meng Qi

    (SC Johnson College of Business, Cornell University, Ithaca, New York 14853)

  • Yuanyuan Shi

    (Department of Electrical and Computer Engineering, University of California–San Diego, San Diego, California 92161)

  • Yongzhi Qi

    (JD.com Smart Supply Chain Y, Mountain View, California 94043)

  • Chenxin Ma

    (JD.com Silicon Valley Research Center, Mountain View, California 94043)

  • Rong Yuan

    (JD.com Silicon Valley Research Center, Mountain View, California 94043)

  • Di Wu

    (JD.com Silicon Valley Research Center, Mountain View, California 94043)

  • Zuo-Jun (Max) Shen

    (SC Johnson College of Business, Cornell University, Ithaca, New York 14853)

Abstract

We 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.

Suggested Citation

  • Meng Qi & Yuanyuan Shi & Yongzhi Qi & Chenxin Ma & Rong Yuan & Di Wu & Zuo-Jun (Max) Shen, 2023. "A Practical End-to-End Inventory Management Model with Deep Learning," Management Science, INFORMS, vol. 69(2), pages 759-773, February.
  • Handle: RePEc:inm:ormnsc:v:69:y:2023:i:2:p:759-773
    DOI: 10.1287/mnsc.2022.4564
    as

    Download full text from publisher

    File URL: http://dx.doi.org/10.1287/mnsc.2022.4564
    Download Restriction: no

    File URL: https://libkey.io/10.1287/mnsc.2022.4564?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Robert S. Kaplan, 1970. "A Dynamic Inventory Model with Stochastic Lead Times," Management Science, INFORMS, vol. 16(7), pages 491-507, March.
    2. Richard Ehrhardt, 1984. "( s , S ) Policies for a Dynamic Inventory Model with Stochastic Lead Times," Operations Research, INFORMS, vol. 32(1), pages 121-132, February.
    3. Alp Muharremoglu & John N. Tsitsiklis, 2008. "A Single-Unit Decomposition Approach to Multiechelon Inventory Systems," Operations Research, INFORMS, vol. 56(5), pages 1089-1103, October.
    4. Retsef Levi & Martin Pál & Robin O. Roundy & David B. Shmoys, 2007. "Approximation Algorithms for Stochastic Inventory Control Models," Mathematics of Operations Research, INFORMS, vol. 32(2), pages 284-302, May.
    5. Afshin Oroojlooyjadid & Lawrence V. Snyder & Martin Takáč, 2020. "Applying deep learning to the newsvendor problem," IISE Transactions, Taylor & Francis Journals, vol. 52(4), pages 444-463, April.
    6. L. Beril Toktay & Lawrence M. Wein, 2001. "Analysis of a Forecasting-Production-Inventory System with Stationary Demand," Management Science, INFORMS, vol. 47(9), pages 1268-1281, September.
    7. Tong Wang & Atalay Atasu & Mümin Kurtuluş, 2012. "A Multiordering Newsvendor Model with Dynamic Forecast Evolution," Manufacturing & Service Operations Management, INFORMS, vol. 14(3), pages 472-484, July.
    8. Dimitris Bertsimas & Nathan Kallus, 2020. "From Predictive to Prescriptive Analytics," Management Science, INFORMS, vol. 66(3), pages 1025-1044, March.
    9. Tetsuo Iida & Paul H. Zipkin, 2006. "Approximate Solutions of a Dynamic Forecast-Inventory Model," Manufacturing & Service Operations Management, INFORMS, vol. 8(4), pages 407-425, October.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Jiaxi Liu & Shuyi Lin & Linwei Xin & Yidong Zhang, 2023. "AI vs. Human Buyers: A Study of Alibaba’s Inventory Replenishment System," Interfaces, INFORMS, vol. 53(5), pages 372-387, September.
    2. Yen, Benjamin P.-C. & Luo, Yu, 2023. "Navigational guidance – A deep learning approach," European Journal of Operational Research, Elsevier, vol. 310(3), pages 1179-1191.
    3. Tian, Yu-Xin & Zhang, Chuan, 2023. "An end-to-end deep learning model for solving data-driven newsvendor problem with accessibility to textual review data," International Journal of Production Economics, Elsevier, vol. 265(C).
    4. Olivares-Nadal, Alba V., 2024. "Constructing decision rules for multiproduct newsvendors: An integrated estimation-and-optimization framework," European Journal of Operational Research, Elsevier, vol. 315(3), pages 1021-1037.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Iida, Tetsuo, 2015. "Benefits of leadtime information and of its combination with demand forecast information," International Journal of Production Economics, Elsevier, vol. 163(C), pages 146-156.
    2. Hekimoğlu, Mustafa & van der Laan, Ervin & Dekker, Rommert, 2018. "Markov-modulated analysis of a spare parts system with random lead times and disruption risks," European Journal of Operational Research, Elsevier, vol. 269(3), pages 909-922.
    3. Van-Anh Truong & Robin O. Roundy, 2011. "Multidimensional Approximation Algorithms for Capacity-Expansion Problems," Operations Research, INFORMS, vol. 59(2), pages 313-327, April.
    4. Zhu, Stuart X., 2017. "Approximate solutions and cost error bounds for quantity flexibility replenishment," International Journal of Production Economics, Elsevier, vol. 193(C), pages 306-315.
    5. Alp Muharremoglu & Nan Yang, 2010. "Inventory Management with an Exogenous Supply Process," Operations Research, INFORMS, vol. 58(1), pages 111-129, February.
    6. Felix Papier, 2016. "Supply Allocation Under Sequential Advance Demand Information," Operations Research, INFORMS, vol. 64(2), pages 341-361, April.
    7. Retsef Levi & Robin O. Roundy & David B. Shmoys & Van Anh Truong, 2008. "Approximation Algorithms for Capacitated Stochastic Inventory Control Models," Operations Research, INFORMS, vol. 56(5), pages 1184-1199, October.
    8. Retsef Levi & Robin Roundy & Van Anh Truong & Xinshang Wang, 2017. "Provably Near-Optimal Balancing Policies for Multi-Echelon Stochastic Inventory Control Models," Mathematics of Operations Research, INFORMS, vol. 42(1), pages 256-276, January.
    9. Ben-Ammar, Oussama & Bettayeb, Belgacem & Dolgui, Alexandre, 2019. "Optimization of multi-period supply planning under stochastic lead times and a dynamic demand," International Journal of Production Economics, Elsevier, vol. 218(C), pages 106-117.
    10. Serrano, Breno & Minner, Stefan & Schiffer, Maximilian & Vidal, Thibaut, 2024. "Bilevel optimization for feature selection in the data-driven newsvendor problem," European Journal of Operational Research, Elsevier, vol. 315(2), pages 703-714.
    11. Boulaksil, Youssef, 2016. "Safety stock placement in supply chains with demand forecast updates," Operations Research Perspectives, Elsevier, vol. 3(C), pages 27-31.
    12. Alexandre Forel & Martin Grunow, 2023. "Dynamic stochastic lot sizing with forecast evolution in rolling‐horizon planning," Production and Operations Management, Production and Operations Management Society, vol. 32(2), pages 449-468, February.
    13. Ganesh Janakiraman & John A. Muckstadt, 2009. "A Decomposition Approach for a Class of Capacitated Serial Systems," Operations Research, INFORMS, vol. 57(6), pages 1384-1393, December.
    14. Van-Anh Truong, 2014. "Approximation Algorithm for the Stochastic Multiperiod Inventory Problem via a Look-Ahead Optimization Approach," Mathematics of Operations Research, INFORMS, vol. 39(4), pages 1039-1056, November.
    15. Awi Federgruen & Min Wang, 2015. "Inventory Models with Shelf-Age and Delay-Dependent Inventory Costs," Operations Research, INFORMS, vol. 63(3), pages 701-715, June.
    16. Paul Zipkin, 2008. "On the Structure of Lost-Sales Inventory Models," Operations Research, INFORMS, vol. 56(4), pages 937-944, August.
    17. Sen Lin & Bo Li & Antonio Arreola-Risa & Yiwei Huang, 2023. "Optimizing a single-product production-inventory system under constant absolute risk aversion," TOP: An Official Journal of the Spanish Society of Statistics and Operations Research, Springer;Sociedad de Estadística e Investigación Operativa, vol. 31(3), pages 510-537, October.
    18. Yang, Cheng-Hu & Wang, Hai-Tang & Ma, Xin & Talluri, Srinivas, 2023. "A data-driven newsvendor problem: A high-dimensional and mixed-frequency method," International Journal of Production Economics, Elsevier, vol. 266(C).
    19. Xiang, Mengyuan & Rossi, Roberto & Martin-Barragan, Belen & Tarim, S. Armagan, 2023. "A mathematical programming-based solution method for the nonstationary inventory problem under correlated demand," European Journal of Operational Research, Elsevier, vol. 304(2), pages 515-524.
    20. Tong Wang & Atalay Atasu & Mümin Kurtuluş, 2012. "A Multiordering Newsvendor Model with Dynamic Forecast Evolution," Manufacturing & Service Operations Management, INFORMS, vol. 14(3), pages 472-484, July.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:inm:ormnsc:v:69:y:2023:i:2:p:759-773. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Chris Asher (email available below). General contact details of provider: https://edirc.repec.org/data/inforea.html .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.