Peer-to-peer loan returns: heterogeneous effects across quantiles

Authors

LYÓCSA Štefan VASANICOVA Petra DEEV Oleg

Year of publication 2024
Type Article in Periodical
Magazine / Source Applied Economics Letters
MU Faculty or unit

Faculty of Economics and Administration

Citation
Web https://www.tandfonline.com/doi/full/10.1080/13504851.2023.2298412
Doi http://dx.doi.org/10.1080/13504851.2023.2298412
Keywords Peer-to-peer loans; loan performance; profit-scoring; quantile regression
Description In this study, we examine how loan and borrowers' characteristics have a different impact on profitable and non-performing loans. Using a quantile regression profit-scoring model estimated with 472,106 loans from the U.S. P2P lending platform Lending Club, we show that higher loan amounts, loan term, interest rate and lower income are associated with lower returns for less creditworthy borrowers, i.e. for under-performed loans. Conversely, for performing loans, higher loan amounts, loan term, interest rates and lower income are associated with higher returns. We also find that borrowers' credit (debt-to-income and FICO score) matters mostly for the tails of the return distribution, to mitigate losses for non-performing loans and improve profits for highest-performing loans. The results have broader implications for the design of credit risk models.

You are running an old browser version. We recommend updating your browser to its latest version.