Network Based Scoring Models to Improve Credit Risk Management in Peer to Peer Lending Platforms

Abstract

Financial intermediation has changed extensively over the course of the last two decades. One of the most significant change has been the emergence of FinTech. In the context of credit services, fintech peer to peer lenders have introduced many opportunities, among which improved speed, better customer experience, and reduced costs. However, peer-to-peer lending platforms lead to higher risks, among which higher credit risk: not owned by the lenders, and systemic risks: due to the high interconnectedness among borrowers generated by the platform. This calls for new and more accurate credit risk models to protect consumers and preserve financial stability. In this paper we propose to enhance credit risk accuracy of peer-to-peer platforms by leveraging topological information embedded into similarity networks, derived from borrowers' financial information. Topological coefficients describing borrowers' importance and community structures are employed as additional explanatory variables, leading to an improved predictive performance of credit scoring models.

Can Readability of Loan Description Affect Loan Success Rate and Loan Cost?: A Textual Analysis of P2P Loan Description

“…P2P lending platforms, which have emerged in recent years (Planuch-Prats & Salvador-Valles, 2018), allow borrowers to bypass financial institutions to directly acquire unsecured loans from individual investors. Compared with traditional financial institutions, characterized by directness and dispersity (Mild, Waitz & Wockl, 2015), P2P lending platforms can treat lenders more equally, reduce financial discrimination (Herzenstein, Andrews, Dholakia & Lyandres, 2008), improve credit services (Balyuk, 2019), lower transaction costs (Hadji Misheva, Spelta & Giudici, 2019), and elevate utilization efficiency of social funds (Duarte, Siegel & Young, 2012). As a new form of decentralized Internet-based financial operation mode, P2P lending platforms have attracted extensive attention from all sectors of society since their creation and achieved rapid development.…”

Network Resilience and Assessment of the Credit Granting Policy

“…Network-based studies of both credit and systemic risk have been explored e.g. by Petrone and Latora 2018and Giudici et al (2019).…”

“…On the contrary, the second work (Giudici et al, 2019) studies how to enhance the estimation accuracy of credit risk of peer-to-peer lending platforms by leveraging topological information embedded into similarity networks, derived from borrowers' financial information. In particular, they use the topological coefficients describing borrowers' importance and community structures derived by a network approach as new independent variables that can be added to a traditional credit scoring model, improving its predicting performance.…”

Factorial Network Models to Improve P2P Credit Risk Management

“…Despite the various advantages, P2P systems inherit some of the challenges of traditional credit risk management. In addition, they are characterized by the asymmetry of information and by a strong interconnectedness among their users (see e.g., Giudici et al, 2019 ) that makes distinguishing healthy and risky credit applicants difficult, thus affecting credit issuers. There is, therefore, a need to explore methods that can help improve credit scoring of individual or companies that engage in P2P credit services.…”

“…Secondly, we extend the network-based scoring model proposed in Giudici et al ( 2019 ) to a setting characterized by a large number of explanatory variables. The variables are selected via lasso-type regularization (Tibshirani, 1996 ; Hastie et al, 2009 ) and, then, summarized by factor scores.…”