Treffer: A hierarchical Bayesian model for payment delay prediction in supply chain financing.

Supply Chain Financing (SCF) has gained importance as a critical tool for improving liquidity and working capital efficiency across supply chains, particularly by enabling suppliers to receive early payments and allowing buyers to extend payment terms without disrupting operations. However, current risk evaluation practices in SCF rely heavily on credit ratings at the company level, which often misalign with the order-level nature of SCF transactions. This misalignment can lead to inaccuracies in assessing payment risk. To address this issue, this paper introduces a Hierarchical Bayesian Model (HBM) that integrates macro-level credit ratings with micro-level order and delivery data to enhance the precision of payment delay predictions. The model not only identifies common behaviour patterns among suppliers, but also offers detailed supplier-specific risk assessments. Through a real-world case study in the aerospace supply chain sector, we demonstrate that HBM significantly outperforms non-hierarchical models in prediction accuracy and provides actionable insights, such as the positive correlation between delivery and payment delays, and the unusual finding that higher credit ratings may be associated with longer payment delays. Our findings suggest that combining company- and order-level data within an interpretable probabilistic framework enhances the explainability and precision of SCF risk assessment. [ABSTRACT FROM AUTHOR]

Copyright of International Journal of Production Research is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Volltext ist im Gastzugang nicht verfügbar. Melden Sie sich für Vollzugriff an.