Credit Risk Analysis for SMEs Using Graph Neural Networks in Supply Chain

TL;DR

This paper presents a GNN-based framework that leverages transaction and social data to improve SME credit risk analysis, especially in data-scarce online lending contexts, with high accuracy demonstrated on real datasets.

Contribution

Introduces a novel GNN framework utilizing SME interaction data for enhanced credit risk prediction and supply chain disruption modeling.

Findings

GNN outperforms traditional models with AUCs of 0.995 and 0.701.

Effective in modeling supply chain disruptions and predicting loan defaults.

Provides scalable tools for regulators and financial institutions.

Abstract

Small and Medium-sized Enterprises (SMEs) are vital to the modern economy, yet their credit risk analysis often struggles with scarce data, especially for online lenders lacking direct credit records. This paper introduces a Graph Neural Network (GNN)-based framework, leveraging SME interactions from transaction and social data to map spatial dependencies and predict loan default risks. Tests on real-world datasets from Discover and Ant Credit (23.4M nodes for supply chain analysis, 8.6M for default prediction) show the GNN surpasses traditional and other GNN baselines, with AUCs of 0.995 and 0.701 for supply chain mining and default prediction, respectively. It also helps regulators model supply chain disruption impacts on banks, accurately forecasting loan defaults from material shortages, and offers Federal Reserve stress testers key data for CCAR risk buffers. This approach provides a scalable, effective tool for assessing SME credit risk.