Evolving Hybrid Deep Neural Network Models for End-to-End Inventory Ordering Decisions

IF 3.6 Q2 MANAGEMENT
Thais de Castro Moraes, Jiancheng Qin, Xue-Ming Yuan, Ek Peng Chew
{"title":"Evolving Hybrid Deep Neural Network Models for End-to-End Inventory Ordering Decisions","authors":"Thais de Castro Moraes, Jiancheng Qin, Xue-Ming Yuan, Ek Peng Chew","doi":"10.3390/logistics7040079","DOIUrl":null,"url":null,"abstract":"Background: Over the past decade, the potential advantages of employing deep learning models and leveraging auxiliary data in data-driven end-to-end (E2E) frameworks to enhance inventory decision-making have gained recognition. However, current approaches predominantly rely on feed-forward networks, which may have difficulty capturing temporal correlations in time series data and identifying relevant features, resulting in less accurate predictions. Methods: Addressing this gap, we introduce novel E2E deep learning frameworks that combine Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) for resolving single-period inventory ordering decisions, also termed the Newsvendor Problem (NVP). This study investigates the performance drivers of hybrid CNN-LSTM architectures, coupled with an evolving algorithm for optimizing network configuration. Results: Empirical evaluation of real-world retail data demonstrates that our proposed models proficiently extract pertinent features and interpret sequential data characteristics, leading to more accurate and informed ordering decisions. Notably, results showcase substantial benefits, yielding up to an 85% reduction in costs compared to a univariate benchmark and up to 40% savings compared to a feed-forward E2E deep learning architecture. Conclusions: This confirms that, in practical scenarios, understanding the impact of features on demand empowers decision-makers to derive tailored, cost-effective ordering decisions for each store or product category.","PeriodicalId":56264,"journal":{"name":"Logistics-Basel","volume":null,"pages":null},"PeriodicalIF":3.6000,"publicationDate":"2023-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Logistics-Basel","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3390/logistics7040079","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MANAGEMENT","Score":null,"Total":0}
引用次数: 0

Abstract

Background: Over the past decade, the potential advantages of employing deep learning models and leveraging auxiliary data in data-driven end-to-end (E2E) frameworks to enhance inventory decision-making have gained recognition. However, current approaches predominantly rely on feed-forward networks, which may have difficulty capturing temporal correlations in time series data and identifying relevant features, resulting in less accurate predictions. Methods: Addressing this gap, we introduce novel E2E deep learning frameworks that combine Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) for resolving single-period inventory ordering decisions, also termed the Newsvendor Problem (NVP). This study investigates the performance drivers of hybrid CNN-LSTM architectures, coupled with an evolving algorithm for optimizing network configuration. Results: Empirical evaluation of real-world retail data demonstrates that our proposed models proficiently extract pertinent features and interpret sequential data characteristics, leading to more accurate and informed ordering decisions. Notably, results showcase substantial benefits, yielding up to an 85% reduction in costs compared to a univariate benchmark and up to 40% savings compared to a feed-forward E2E deep learning architecture. Conclusions: This confirms that, in practical scenarios, understanding the impact of features on demand empowers decision-makers to derive tailored, cost-effective ordering decisions for each store or product category.
端到端库存排序决策的进化混合深度神经网络模型
背景:在过去的十年中,在数据驱动的端到端(E2E)框架中使用深度学习模型和利用辅助数据来增强库存决策的潜在优势已经得到了认可。然而,目前的方法主要依赖于前馈网络,这可能难以捕获时间序列数据中的时间相关性并识别相关特征,从而导致预测的准确性较低。方法:为了解决这一问题,我们引入了新的端到端深度学习框架,该框架结合了卷积神经网络(CNN)和长短期记忆(LSTM)来解决单周期库存订购决策,也称为报贩问题(NVP)。本研究探讨了混合CNN-LSTM架构的性能驱动因素,并结合了优化网络配置的进化算法。结果:对真实零售数据的实证评估表明,我们提出的模型能够熟练地提取相关特征并解释序列数据特征,从而做出更准确、更明智的订购决策。值得注意的是,结果显示出了巨大的优势,与单变量基准测试相比,成本降低了85%,与前馈E2E深度学习架构相比,成本降低了40%。结论:这证实了,在实际场景中,了解功能对需求的影响使决策者能够为每个商店或产品类别制定量身定制的、具有成本效益的订购决策。
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 求助全文
来源期刊
Logistics-Basel
Logistics-Basel Multiple-
CiteScore
6.60
自引率
0.00%
发文量
0
审稿时长
11 weeks
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信