IDEAS home Printed from https://ideas.repec.org/a/inm/orinte/v53y2023i5p372-387.html
   My bibliography  Save this article

AI vs. Human Buyers: A Study of Alibaba’s Inventory Replenishment System

Author

Listed:
  • Jiaxi Liu

    (Alibaba Group, Hangzhou, Zhejiang 311100, China)

  • Shuyi Lin

    (Alibaba Group, Hangzhou, Zhejiang 311100, China)

  • Linwei Xin

    (Booth School of Business, University of Chicago, Chicago, Illinois 60637)

  • Yidong Zhang

    (Alibaba Group, Hangzhou, Zhejiang 311100, China)

Abstract

Inventory management is one of the most important components of Alibaba’s business. Traditionally, human buyers make replenishment decisions: although artificial intelligence (AI) algorithms make recommendations, human buyers can choose to ignore these recommendations and make their own decisions. The company has been exploring a new replenishment system in which algorithmic recommendations are final. The algorithms combine state-of-the-art deep reinforcement learning techniques with the framework of fictitious play. By learning the supplier’s behavior, we are able to address the important issues of lead time and fill rate on order quantity, which have been ignored in the extant literature of stochastic inventory control. We present evidence that our algorithms outperform human buyers in terms of reducing out-of-stock rates and inventory levels. More interestingly, we have seen additional benefits amid the pandemic. Over the last two years, cities in China partially and intermittently locked down to mitigate COVID-19 outbreaks. We have observed panic buying from human buyers during lockdowns, leading to the bullwhip effect. By contrast, panic buying and the bullwhip effect can be mitigated using our algorithms due to their ability to recognize changes in the supplier’s behavior during lockdowns.

Suggested Citation

  • 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.
  • Handle: RePEc:inm:orinte:v:53:y:2023:i:5:p:372-387
    DOI: 10.1287/inte.2023.1160
    as

    Download full text from publisher

    File URL: http://dx.doi.org/10.1287/inte.2023.1160
    Download Restriction: no

    File URL: https://libkey.io/10.1287/inte.2023.1160?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. Linwei Xin & David A. Goldberg, 2016. "Optimality Gap of Constant-Order Policies Decays Exponentially in the Lead Time for Lost Sales Models," Operations Research, INFORMS, vol. 64(6), pages 1556-1565, December.
    2. David Silver & Julian Schrittwieser & Karen Simonyan & Ioannis Antonoglou & Aja Huang & Arthur Guez & Thomas Hubert & Lucas Baker & Matthew Lai & Adrian Bolton & Yutian Chen & Timothy Lillicrap & Fan , 2017. "Mastering the game of Go without human knowledge," Nature, Nature, vol. 550(7676), pages 354-359, October.
    3. 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.
    4. Berger, Ulrich, 2007. "Brown's original fictitious play," Journal of Economic Theory, Elsevier, vol. 135(1), pages 572-578, July.
    5. David A. Goldberg & Dmitriy A. Katz-Rogozhnikov & Yingdong Lu & Mayank Sharma & Mark S. Squillante, 2016. "Asymptotic Optimality of Constant-Order Policies for Lost Sales Inventory Models with Large Lead Times," Mathematics of Operations Research, INFORMS, vol. 41(3), pages 898-913, August.
    Full references (including those not matched with items on IDEAS)

    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. Shenghai Zhou & Yichuan Ding & Woonghee Tim Huh & Guohua Wan, 2021. "Constant Job‐Allowance Policies for Appointment Scheduling: Performance Bounds and Numerical Analysis," Production and Operations Management, Production and Operations Management Society, vol. 30(7), pages 2211-2231, July.
    2. Xiuli Chao & Xiting Gong & Cong Shi & Chaolin Yang & Huanan Zhang & Sean X. Zhou, 2018. "Approximation Algorithms for Capacitated Perishable Inventory Systems with Positive Lead Times," Management Science, INFORMS, vol. 64(11), pages 5038-5061, November.
    3. Hailun Zhang & Jiheng Zhang & Rachel Q. Zhang, 2020. "Simple Policies with Provable Bounds for Managing Perishable Inventory," Production and Operations Management, Production and Operations Management Society, vol. 29(11), pages 2637-2650, November.
    4. Jinzhi Bu & Xiting Gong & Dacheng Yao, 2019. "Technical Note—Constant-Order Policies for Lost-Sales Inventory Models with Random Supply Functions: Asymptotics and Heuristic," Operations Research, INFORMS, vol. 68(4), pages 1063-1073, July.
    5. Boute, Robert N. & Gijsbrechts, Joren & van Jaarsveld, Willem & Vanvuchelen, Nathalie, 2022. "Deep reinforcement learning for inventory control: A roadmap," European Journal of Operational Research, Elsevier, vol. 298(2), pages 401-412.
    6. Jinzhi Bu & Xiting Gong & Xiuli Chao, 2023. "Asymptotic Optimality of Base-Stock Policies for Perishable Inventory Systems," Management Science, INFORMS, vol. 69(2), pages 846-864, February.
    7. Li, Zhaolin (Erick) & Liang, Guitian & Fu, Qi (Grace) & Teo, Chung-Piaw, 2023. "Base-Stock Policies with Constant Lead Time: Closed-Form Solutions and Applications," Working Papers BAWP-2023-01, University of Sydney Business School, Discipline of Business Analytics.
    8. Huanan Zhang & Xiuli Chao & Cong Shi, 2020. "Closing the Gap: A Learning Algorithm for Lost-Sales Inventory Systems with Lead Times," Management Science, INFORMS, vol. 66(5), pages 1962-1980, May.
    9. Linwei Xin & David A. Goldberg, 2018. "Asymptotic Optimality of Tailored Base-Surge Policies in Dual-Sourcing Inventory Systems," Management Science, INFORMS, vol. 64(1), pages 437-452, January.
    10. Linwei Xin, 2021. "Technical Note—Understanding the Performance of Capped Base-Stock Policies in Lost-Sales Inventory Models," Operations Research, INFORMS, vol. 69(1), pages 61-70, January.
    11. Daníelsson, Jón & Macrae, Robert & Uthemann, Andreas, 2022. "Artificial intelligence and systemic risk," Journal of Banking & Finance, Elsevier, vol. 140(C).
    12. Zhang, Xi & Wang, Qin & Bi, Xiaowen & Li, Donghong & Liu, Dong & Yu, Yuanjin & Tse, Chi Kong, 2024. "Mitigating cascading failure in power grids with deep reinforcement learning-based remedial actions," Reliability Engineering and System Safety, Elsevier, vol. 250(C).
    13. Yanyi Xu & Doğan A. Serel & Arnab Bisi & Maqbool Dada, 2022. "Coping with Demand Uncertainty: The Interplay between Dual Sourcing and Endogenous Partial Backordering," Production and Operations Management, Production and Operations Management Society, vol. 31(4), pages 1560-1575, April.
    14. Linwei Xin & David A. Goldberg, 2016. "Optimality Gap of Constant-Order Policies Decays Exponentially in the Lead Time for Lost Sales Models," Operations Research, INFORMS, vol. 64(6), pages 1556-1565, December.
    15. Adnan Jafar & Alessandra Kobayati & Michael A. Tsoukas & Ahmad Haidar, 2024. "Personalized insulin dosing using reinforcement learning for high-fat meals and aerobic exercises in type 1 diabetes: a proof-of-concept trial," Nature Communications, Nature, vol. 15(1), pages 1-12, December.
    16. Yang, Zhengzhi & Zheng, Lei & Perc, Matjaž & Li, Yumeng, 2024. "Interaction state Q-learning promotes cooperation in the spatial prisoner's dilemma game," Applied Mathematics and Computation, Elsevier, vol. 463(C).
    17. Stefan Rass & Sandra König & Stefan Schauer, 2017. "Defending Against Advanced Persistent Threats Using Game-Theory," PLOS ONE, Public Library of Science, vol. 12(1), pages 1-43, January.
    18. Artur Kwasek & Maria Kocot & Izabela Gontarek & Igor Protasowicki & Bartosz Blaszczak, 2024. "Negative Faces of Artificial Intelligence in the Conditions of the Knowledge-Based Economy," European Research Studies Journal, European Research Studies Journal, vol. 0(2), pages 465-477.
    19. Zhang, Yihao & Chai, Zhaojie & Lykotrafitis, George, 2021. "Deep reinforcement learning with a particle dynamics environment applied to emergency evacuation of a room with obstacles," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 571(C).
    20. Keller, Alexander & Dahm, Ken, 2019. "Integral equations and machine learning," Mathematics and Computers in Simulation (MATCOM), Elsevier, vol. 161(C), pages 2-12.

    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:orinte:v:53:y:2023:i:5:p:372-387. 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.