Leveraging Network Topology for Credit Risk Assessment in P2P Lending: A Comparative Study under the Lens of Machine Learning

Abstract

Peer-to-Peer (P2P) lending markets have witnessed remarkable growth, revolutionizing the way borrowers and lenders interact. Despite their increasing popularity, P2P lending poses significant challenges related to credit risk assessment and default prediction with meaningful implications for financial stability. Traditional credit risk models have been widely employed in the field of P2P lending; however, they may not be fully capable to capture the complexity of the loan networks and the nuances of borrower behavior that are specifically evident in P2P lending markets. Thus, in this study we propose an enhanced two-step machine learning (ML) approach that first utilises insights from network analysis and subsequently combines derived network centrality metrics with traditional credit risk factors to improve the prediction accuracy in the credit risk modelling process.

Keywords: P2P-lending, Credit-Default Prediction, Machine Learning (ML), Network Centrality

JEL Classification: G00, G1, G12, G14, G02, G4