Data-driven optimization models for inventory and financing decisions in online retailing platforms

Bingnan Yang (), Xianhao Xu (), Yeming Gong () and Yacine Rekik ()
Additional contact information
Bingnan Yang: Huazhong University of Science and Technology
Xianhao Xu: Huazhong University of Science and Technology
Yeming Gong: Emlyon Business School
Yacine Rekik: ESCP Business School

Annals of Operations Research, 2024, vol. 339, issue 1, No 27, 764 pages

Abstract: Abstract With data-driven optimization, this study investigates the sellers’ inventory replenishment and financial decisions, and lenders’ interest rate decisions in online retailing platforms. Moreover, we focus on the annual large-scale promotion, which requires massive capital in a short period. While scholars studying the data-driven inventory replenishment problem hardly consider capital-constrained sellers, these problems are important because the seller’s capital level can significantly influence the order quantity and generate different effects on inventory management. Hence, we propose two novel data-driven game-theoretic approaches (including separated and integrated methods) using machine learning and deep learning methods to optimize inventory replenishment and financial decisions for the sellers who obtain financial support from the online platform. Moreover, we propose a data-driven game-theoretic model for the online platform to optimize their interest rate considering the market potential. We explore the real retailing transaction data containing 199,390 weekly sales records. We find that the seller and lender can benefit when the seller chooses integrated machine learning and quantile regression method. However, we find that only a low capital level can motivate the seller to choose to borrow from the lender. Interestingly, our results also suggest that the lender has the motivation to build a data-driven system that helps sellers optimize inventory decisions. Our work identifies the optimal interest rate and inventory decision under the data-driven method. We propose data-driven decision support tools by evaluating the values of both the lender’s and the seller’s profit and provide new management insights on joint inventory and financing decisions.

Keywords: Data-driven decision making and analytics; Capital constraints; Machine learning; Deep learning; Online retailing (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10479-023-05234-4 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

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:spr:annopr:v:339:y:2024:i:1:d:10.1007_s10479-023-05234-4

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10479

DOI: 10.1007/s10479-023-05234-4

Access Statistics for this article

Annals of Operations Research is currently edited by Endre Boros

More articles in Annals of Operations Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().