Culminating Project Title
Date of Award
Culminating Project Type
Applied Economics: M.S.
School of Public Affairs
Lynn A. Collen
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Keywords and Subject Headings
Peer-to-Peer Lending, Credit Risk, FICO, P2P Loan Default, Consumer Credit, Logistic Regression.
Credit Risk in Peer to Peer Lending is an emerging field with practical implications for U.S banking system. Peer to Peer Lending is a type of online lending process which uses nontraditional bank channels. The inexorable rise of Fintechs has led to an extraordinary change in financial intermediation. This paper examines the factors that are critical in predicting default in Peer to Peer lending. The paper finds that FICO score, debt-to-income ratio , the loan amount, the credit grade assigned by the online lending platform are all critical factors of the credit risk evaluation process. Furthermore, models with hyperparameters such as neural networks and random forest do not reliably outperform classical logistic regression in the prediction of credit default. Finally, this paper makes vital policy recommendations to strengthen the efficiency of marketplace lending and provides a set of rules to prevent another crisis of the magnitude of the great recession.
Coulibaly, Aboubacar, "Credit Risk Estimation in the Age of Peer to Peer Lending" (2019). Culminating Projects in Economics. 14.