Swiss National Science Foundation (SNF): Network-based credit risk models in P2P lending markets

From EU COST Fin-AI
Jump to navigation Jump to search

Introduction

P2P (peer-to-peer) lending has emerged as a significant financial innovation, allowing individuals and businesses to secure loans without the intermediation of traditional banks. These platforms offer a secure online environment where borrowers and investors engage in a bidding process until the loan is fully funded. Despite the advantages, such as higher interest rates for lenders and lower operational costs for platforms, P2P lending markets are fraught with challenges. They are characterized as immature industries with loose regulation, greater information asymmetry, and increased credit risk, leading to higher default rates.

In this complex landscape, the role of accurate credit risk models becomes paramount. The main objective of this research project is to design state-of-the-art and interpretable credit risk models specifically tailored for P2P lending markets. These models aim to mitigate adverse selection and moral hazard problems, thereby building trust and making the financial environment more stable.

Project Objectives

As the research begins, the main goal of the project is to develop accurate and easy-to-understand credit risk models for the P2P (peer-to-peer) lending industry. These models will be based on network-based methods and will be used to identify whether or not a borrower represents a good credit risk in the P2P lending market. Other objectives of the project include:

  • Examining the factors that lead to the success or failure of P2P lending platforms
  • Examining how economics and the market influence peer-to-peer lending
  • Examining how trust is built in peer-to-peer lending
  • Advancing network science

Upon completion of the project, key results and insights should be available on how well the credit risk models can predict default rates in the P2P lending market, as well as any other factors that impact the success or failure of P2P lending platforms. Based on the results and lessons learned, the project could also provide suggestions for further research. The objectives of the project will be achieved if the credit risk models created can accurately assess the creditworthiness of borrowers in the P2P lending market and help make the financial environment in these new markets more stable.

Accurate credit risk models are important for the long-term growth of peer-to-peer credit markets and for stabilizing the financial world. These models can help reduce the risks of P2P lending by accurately assessing borrowers' creditworthiness and giving investors the information they need to make smart decisions. The development of new, innovative credit risk models based on network-based methods will be of great help to the financial sector. These models will also be useful in other research areas where feature selection and extraction are important.

The social context of this research is the increasing use of digital financial services, such as: B. Peer-to-peer lending, which could make credit and financial services easier for everyone to access. By examining the risks of P2P lending, this research can help make the financial world more stable and durable for both borrowers and investors.

Scientific Abstract

P2P (peer-to-peer) lending today consists of the lending of money to individuals and businesses through online services without bank intermediation (Thakor, 2020). P2P platforms offer a secure cyberspace (Niu et al., 2020) where borrowers are linked to investors who engage (usually) in a buyout auction, where the bidding process ends when the loan has been fully funded (Xia et al., 2017). Bank lending is backed by deposits, uninsured debt and equity; thus, banks have skin in the game, unlike P2P lending platforms, where loans are funded by investors directly, i.e., through investors’ equity. Higher interest rates and diversification potential incentivize lenders, represented by individuals and recently also by banks, hedge funds, venture capital firms and private equity firms (Giudici et al. 2019a), to participate in P2P lending. Traditional banks receive loan repayments that are used to pay out depositors, subordinated debt holders and potentially shareholders, while P2P platforms receive fees from loan origination (paid by the borrower) and transaction fees. Administration of lending tends to be cheaper for P2P platforms, which provide an online marketplace and initial risk classification, while banks are subject to much tighter regulation and thus have higher costs (Thakor, 2020). However, banks have much richer data at their disposal (e.g., through long-term relational banking), which makes their task of identifying potential nonperforming loans easier. One would therefore expect P2P platforms to attract borrowers who would otherwise not be eligible for bank loans. This effect is amplified during recessions, as reduced access to bank credit directs riskier borrowers towards the P2P markets. This phenomenon has been observed empirically, as several studies have found that after the 2008 recession, the growth of P2P markets accelerated (e.g., Jin and Zhu, 2015). Similar growth is likely to unfold during and after the current worldwide economic crisis induced by the COVID-19 pandemic.Given the nature of P2P markets, they are characterized as immature industries with loose regulation, greater information asymmetry and increased credit risk, which all lead to higher default rates. This leaves the door open to considerable risks. To mitigate adverse selection and moral hazard problems, one needs to build trust. In traditional bank-lending markets, trust is constructed via relational banking, using collateral, certified accounts, risk monitoring, the presence of a board of directors, tighter regulation, etc. (Emekter, 2015). Voluntary implementation of these mechanisms would incur significant costs and thus marginalize the competitive edge of P2P lending markets. Several recent studies have found that the failure of P2P platforms in China is related to general market conditions (bond yields), ownership, information disclosure, and popularity, while political ties were found to also play an important role (e.g., Gao et al., 2021, He and Li, 2021). A hands-on approach to establishing trust between investors and P2P markets is to use accurate credit risk models. The main objective of the proposed research project is to design a state-of-the art and interpretable credit risk models for P2P lending markets.

Research Plan and Methods

Detailed Research Plan Including Methods and Timeline

  • Phase I: Data Preparation

Data preprocessing & updates for multiple data sources Updates of existing literature

  • Phase II: Development of New Network-Based Features

Threshold networks and different distance measures Cross-validated networks—centrality measures Cross-validated networks—cluster-based measures Default and nondefault similarity network measures Bagging networks

  • Phase III: Empirical Models & XAI

Estimation of network-based credit risk models Tests of applicability of XAI and robustness of explanations to new credit risk models Preparing research outcomes

Timeline: Spanning three years from 2022 to 2024 Expected Outcomes: Original research articles to be prepared in Phase III, presented in workshops and conferences, and submitted for publication in peer-reviewed journals.

Persons

Applicants

  • Joerg Osterrieder, Departement Wirtschaft Berner Fachhochschule BFH, Switzerland
  • Baumohl Eduard, Institute of Financial Complex Systems Faculty of Economics and Administration Masaryk University, Czech Republic
  • Peter Schwendner, Institut für Wealth & Asset Management School of Management and Law ZHAW, Switzerland

Principal Investigator

  • Branka Hadji Misheva, Departement Wirtschaft Berner Fachhochschule BFH, Switzerland

Employees

  • Lennart Baals
  • Liu Yiting

Disciplines and keywords

Economics P2P, graph theory, credit scoring, XAI

Conclusion

The project aims to make a groundbreaking contribution to the field of P2P lending by developing state-of-the-art credit risk models based on network-based methods. These models are expected to significantly improve the assessment of borrowers' creditworthiness, thereby stabilizing the financial environment in P2P lending markets. The project also aims to advance network science and contribute to the broader financial sector.

The social context of this research is particularly relevant given the increasing use of digital financial services. By examining the risks associated with P2P lending, the project aims to make the financial world more stable and durable for both borrowers and investors.

Upon successful completion, the project is expected to provide key insights into the factors that impact the success or failure of P2P lending platforms. These insights could be invaluable for regulatory bodies, financial institutions, and individual investors.

Future directions for this research could include the application of the developed models to other types of lending markets and financial instruments. Additionally, the project could pave the way for further research into the integration of advanced machine learning techniques in credit risk assessment.

This concludes the overview of the research project. The objectives set forth are ambitious yet achievable, and the project is poised to make a significant impact on both the academic and practical aspects of P2P lending.

Links

For more details, visit the Project on SNF webpage.

Retrieved from "https://wiki.fin-ai.eu/index.php?title=Swiss_National_Science_Foundation_(SNF):_Network-based_credit_risk_models_in_P2P_lending_markets&oldid=79609"