Services on Demand
Journal
Article
Indicators
- Cited by SciELO
- Access statistics
Related links
- Similars in SciELO
Share
Análisis económico
On-line version ISSN 2448-6655Print version ISSN 0185-3937
Abstract
MOTA ARAGON, Martha Beatriz and MONCAYO MEJIA, Pamela. An analysis of risk profiles in peer-to-peer lending through K-Means Clustering. Anál. econ. [online]. 2023, vol.38, n.99, pp.119-144. Epub Sep 25, 2023. ISSN 2448-6655. https://doi.org/10.24275/uam/azc/dcsh/ae/2023v38n99/mota.
We empirically analyze the LendingClub dataset, the pioneer of the peer-to-peer digital lending market. We aim to contextualize the business model through its database and the variables involved in the risk profile of the participants. We consider four different periods to capture economic cycles and their impact on the credit profile of borrowers. We implement K-Means Clustering Analysis to analytically define a segmentation pattern for participants based on the interest rate of the loans and the FICO (Fair Isaac Company) score. The clusters are constant throughout the periods studied and allow to detect average income levels, issued loans destination and borrower geographic origin according to risk profile. Few studies contemplate all the information available for the LendingClub operation (2007-2020Q3), therefore, this study illustrates how this business model has transitioned to maturity. This work achieves two objectives: to demonstrate the evolution of clients and the platform over time in terms of the risk profiles of participating borrowers, and to highlight the use of K-Means Clustering as an appropriate tool for profiling against to other analytical alternatives.
Keywords : K-Means Clustering; LendingClub; Fintech; Peer-to-peer lending; Credit Risk.