Pooling and Boosting for Demand Prediction in Retail: A Transfer Learning Approach

Dazhou Lei, Yongzhi Qi, Sheng Liu, Dongyang Geng, Jianshen Zhang, Hao Hu, Zuo-Jun Max Shen
{"title":"Pooling and Boosting for Demand Prediction in Retail: A Transfer Learning Approach","authors":"Dazhou Lei, Yongzhi Qi, Sheng Liu, Dongyang Geng, Jianshen Zhang, Hao Hu, Zuo-Jun Max Shen","doi":"10.1287/msom.2022.0453","DOIUrl":null,"url":null,"abstract":"Problem definition: How should retailers leverage aggregate (category) sales information for individual product demand prediction? Motivated by inventory risk pooling, we develop a new prediction framework that integrates category-product sales information to exploit the benefit of pooling. Methodology/results: We propose to combine data from different aggregation levels in a transfer learning framework. Our approach treats the top-level sales information as a regularization for fitting the bottom-level prediction model. We characterize the error performance of our model in linear cases and demonstrate the benefit of pooling. Moreover, our approach exploits a natural connection to regularized gradient boosting trees that enable a scalable implementation for large-scale applications. Based on an internal study with JD.com on more than 6,000 weekly observations between 2020 and 2021, we evaluate the out-of-sample forecasting performance of our approach against state-of-the-art benchmarks. The result shows that our approach delivers superior forecasting performance consistently with more than 9% improvement over the benchmark method of JD.com . We further validate its generalizability on a Walmart retail data set and through alternative pooling and prediction methods. Managerial implications: Using aggregate sales information directly may not help with product demand prediction. Our result highlights the value of transfer learning to demand prediction in retail with both theoretical and empirical support. Based on a conservative estimate of JD.com , the improved forecasts can reduce the operating cost by 0.01–0.29 renminbi (RMB) per sold unit on the retail platform, which implies significant cost savings for the low-margin e-retail business.History: This paper has been accepted as part of the 2023 Manufacturing & Service Operations Management Practice-Based Research Competition.Funding: This work was supported by the National Natural Science Foundation of China [Grant 71991462].Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2022.0453 .","PeriodicalId":501267,"journal":{"name":"Manufacturing & Service Operations Management","volume":"42 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Manufacturing & Service Operations Management","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1287/msom.2022.0453","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Problem definition: How should retailers leverage aggregate (category) sales information for individual product demand prediction? Motivated by inventory risk pooling, we develop a new prediction framework that integrates category-product sales information to exploit the benefit of pooling. Methodology/results: We propose to combine data from different aggregation levels in a transfer learning framework. Our approach treats the top-level sales information as a regularization for fitting the bottom-level prediction model. We characterize the error performance of our model in linear cases and demonstrate the benefit of pooling. Moreover, our approach exploits a natural connection to regularized gradient boosting trees that enable a scalable implementation for large-scale applications. Based on an internal study with JD.com on more than 6,000 weekly observations between 2020 and 2021, we evaluate the out-of-sample forecasting performance of our approach against state-of-the-art benchmarks. The result shows that our approach delivers superior forecasting performance consistently with more than 9% improvement over the benchmark method of JD.com . We further validate its generalizability on a Walmart retail data set and through alternative pooling and prediction methods. Managerial implications: Using aggregate sales information directly may not help with product demand prediction. Our result highlights the value of transfer learning to demand prediction in retail with both theoretical and empirical support. Based on a conservative estimate of JD.com , the improved forecasts can reduce the operating cost by 0.01–0.29 renminbi (RMB) per sold unit on the retail platform, which implies significant cost savings for the low-margin e-retail business.History: This paper has been accepted as part of the 2023 Manufacturing & Service Operations Management Practice-Based Research Competition.Funding: This work was supported by the National Natural Science Foundation of China [Grant 71991462].Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2022.0453 .
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
零售业需求预测的集合和提升:迁移学习法
问题定义:零售商应如何利用总体(品类)销售信息来预测单个产品的需求?受库存风险池的启发,我们开发了一个新的预测框架,该框架整合了品类-产品销售信息,以利用库存风险池的优势。方法/结果:我们建议在迁移学习框架中结合来自不同汇总层的数据。我们的方法将顶层销售信息作为拟合底层预测模型的正则化处理。我们描述了模型在线性情况下的误差性能,并证明了汇集数据的好处。此外,我们的方法与正则化梯度提升树有着天然的联系,可以为大规模应用提供可扩展的实施方案。基于与 JD.com 在 2020 年至 2021 年期间对 6000 多个每周观测数据进行的内部研究,我们对照最先进的基准评估了我们的方法的样本外预测性能。结果表明,与 JD.com 的基准方法相比,我们的方法持续提供卓越的预测性能,改进幅度超过 9%。我们还在沃尔玛零售数据集上进一步验证了该方法的通用性,并通过其他池化和预测方法进行了验证。管理意义:直接使用总体销售信息可能无助于产品需求预测。我们的研究结果凸显了迁移学习在零售业需求预测中的价值,并得到了理论和实践的支持。根据对 JD.com 的保守估计,改进后的预测可以将零售平台上每销售单位的运营成本降低 0.01-0.29 元人民币,这意味着低利润率的电子零售业务可以节省大量成本:该论文已被2023年制造业& 服务业运营管理实践研究竞赛录用:本研究得到了国家自然科学基金[批准号:71991462]的资助:在线附录见 https://doi.org/10.1287/msom.2022.0453 。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Competition in Optimal Stopping: Behavioral Insights Information Dependency in Mitigating Disruption Cascades Adaptive Two-Stage Stochastic Programming with an Analysis on Capacity Expansion Planning Problem Demand Equilibria in Spatial Service Systems Optimal Salesforce Compensation with General Demand and Operational Considerations
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1