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

Thais de Castro Moraes (), Jiancheng Qin, Xue-Ming Yuan and Ek Peng Chew
Additional contact information
Thais de Castro Moraes: Singapore Institute of Manufacturing Technology (SIMTech), Agency for Science, Technology and Research (A*STAR), Singapore 138634, Singapore
Jiancheng Qin: Department of Industrial Systems Engineering and Management, College of Design and Engineering, National University of Singapore, Singapore 119077, Singapore
Xue-Ming Yuan: Singapore Institute of Manufacturing Technology (SIMTech), Agency for Science, Technology and Research (A*STAR), Singapore 138634, Singapore
Ek Peng Chew: Department of Industrial Systems Engineering and Management, College of Design and Engineering, National University of Singapore, Singapore 119077, Singapore

Logistics, 2023, vol. 7, issue 4, 1-18

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.

Keywords: inventory optimization; newsvendor problem; deep learning; CNN-LSTM; evolving algorithms; end-to-end approaches (search for similar items in EconPapers)
JEL-codes: L8 L80 L81 L86 L87 L9 L90 L91 L92 L93 L98 L99 M1 M10 M11 M16 M19 R4 R40 R41 R49 (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2305-6290/7/4/79/pdf (application/pdf)
https://www.mdpi.com/2305-6290/7/4/79/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jlogis:v:7:y:2023:i:4:p:79-:d:1273141

Access Statistics for this article

Logistics is currently edited by Ms. Mavis Li

More articles in Logistics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().