Paolo Giudici, University of Pavia, Italy

Applied statistics workshop 
Paolo Giudici, Fintech laboratory, Department of Economics and management, University of Pavia, Italy
"Network based credit risk models for Peer to peer lending"

Abstract:

Among Financial Technologies, Peer-to-Peer lending platforms may lead to cost reduction, and to an improved user experience. However, these improvements may come at the price of inaccurate credit risk measurements, and to related contagion risks, which  may hamper lenders and endanger the stability of a financial system. In the talk, we propose how to improve credit risk accuracy of peer to peer platforms and, specifically, of those who lend to small and medium enterprises, by leveraging borrowers' networking data. To achieve this goal, we propose to augment traditional credit scoring methods with centrality measures derived from similarity networks among borrowers, deduced from the comovement of their financial variables. Our findings show that the inclusion of network centralities does improve the predictive accuracy of credit scoring models and that, in addition, it enhances  model explainability.