Balancing Risk and Reward: Unveiling the Credit Conundrum in P2P Lending – A Tale of Default and Profit Scoring

Marko Dávid VATEHA

https://doi.org/10.53465/EDAMBA.2023.9788022551274.282-291

 

Abstract. A credit risk assessment is a vital component of the lending process, particularly in the rapidly growing realm of peer-to-peer (P2P) lending. This empirical study delves into the credit risk assessment methods of default and profit scoring, employing machine learning techniques on a publicly available dataset sourced from P2P lending platform – Lending Club. Our investigation yields insightful findings, emphasizing the paramount importance of accurate credit risk evaluation and their implications for loan portfolio returns. The outcomes of our analysis reveal that profit scoring outperforms default scoring in terms of higher annualized returns on loan portfolio. Notably, this superior performance of profit scoring is primarily attributed to its ability to intelligently accept more loans. This is due to the fact that traditional default modelling approaches do not take into account the possibility that certain defaulted loans would generate positive annualized returns as debtors may default at the end of the loan life cycle. By considering not only the risk of default but also the potential profitability of a loan, profit scoring enables lenders to make informed decisions and optimize their portfolio returns effectively. Our findings further reinforce the need for lenders to adopt advanced credit risk modelling techniques, such as profit scoring, to navigate the dynamic P2P lending landscape successfully.

Keywords: P2P Lending, Default, Profit Scoring, Machine Learning

JEL classification: G21, C55

Fulltext: PDF

Online publication date: 25 January 2024

ISBN: 978-80-225-5127-4

Publisher: University of Economics in Bratislava

Pages: 282-291

 

To cite this proceedings paper (STN ISO 690 and 690-2): 

VATEHA, D., M. 2024. Balancing Risk and Reward: Unveiling the Credit Conundrum in P2P Lending - A Tale of Default and Profit Scoring. In PETROVSKÁ, F. (ed.). EDAMBA 2023: Conference Proceedings. Bratislava: University of Economics in Bratislava, 2024. ISBN 978-80-225-5127-4, pp. 282-291.

https://doi.org/10.53465/EDAMBA.2023.9788022551274.282-291