Portfolio Choice for Online Loans and Implications for Platforms

Information Systems and Operations Management (ISOM)

Speaker : Ram GOPAL

From Warwick Business School

Room : Bernard Ramanantsoa

"Using over one million LendingClub loans from 2013 to 2020, we investigate the suitability of online loans as an investment through the lens of a portfolio optimization framework. We propose a dual-layer framework that combines machine learning and parametric portfolio optimization to overcome unique challenges associated with building a portfolio of online loans. Whereas a naive equal-weight portfolio achieves an average 36-month return on investment of 4.03%, the dual-layer approach leads to an improved ROI of 6.69%. To assess the attractiveness of online loans, we compare the performance of the dual-layer portfolio to that of the S&P 500 Index. We find that in our sample, online loans earn competitive rates of return to the S&P 500 while showing limited comovement. Our results indicate that online loans are an attractive novel asset class for investors, and those with heavy stock market exposure can diversify their holdings by investing in online loans without sacrificing expected returns. Platforms may consider embedding a dual-layer portfolio framework in a robo-advising system, which would expand the access of sophisticated loan portfolios to a broad set of investors. "