Modeling (and Learning from) Inventory Inaccuracies in E‐retailing/B2B contexts - Université Claude Bernard Lyon 1 Accéder directement au contenu
Article Dans Une Revue Decision Sciences Année : 2019

Modeling (and Learning from) Inventory Inaccuracies in E‐retailing/B2B contexts

Résumé

Practical experience and scientific research show that there is scope for improving the performance of inventory control systems by taking into account the discrepancies between the actual physical inventory levels and those recorded in the information system (IS). Such discrepancies, which are often referred to as inventory (record) inaccuracies, are a major concern in contemporary supply chains where commitments to orders are usually made based on IS records only. Empirical data obtained in two case studies motivate the development of a multiperiod inventory control model that explicitly accounts for the differences between physical inventory levels and IS stock records. Numerical experiments help derive some key managerial insights. We find that previous important results on the behavior of the optimal order quantity in the retailing environment do not necessarily apply in an e‐retailing/Business‐To‐Business (B2B) context. We adjust and apply the zero balance walk technique to the e‐retailing/B2B case and deduce a simple and efficient learning mechanism about the errors’ distributions. We close with an agenda for further research in this area.

Dates et versions

hal-02159631 , version 1 (18-06-2019)

Identifiants

Citer

Yacine Rekik, Aris Syntetos, Christoph H. Glock. Modeling (and Learning from) Inventory Inaccuracies in E‐retailing/B2B contexts. Decision Sciences, 2019, ⟨10.1111/deci.12367⟩. ⟨hal-02159631⟩
145 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More