How Does a Firm Adapt in a Changing World? The Case of Prosper Marketplace

Abstract

We propose a generalized revealed preference approach to infer how a firm adapts to a changing environment. We apply this approach to Prosper, which is a peer-to-peer lending platform. To implement our approach, we develop a structural model, in which Prosper uses an adaptive learning algorithm to continuously update its predictive models about borrowers' and lenders' behavior as more data become available, and uses these updated models to help assign loan ratings over time. To infer which adaptive learning algorithm Prosper may adopt, we consider a set of algorithms motivated by the machine learning literature. For each algorithm, we use observed Prosper’s loan rating decisions to estimate the structural parameters of Prosper’s objective function. By comparing the goodness-of-fit of these algorithm-specific models, we find that Prosper most likely uses an ensemble algorithm which selects past observations based on their economic conditions. We also find evidence that Prosper values both expected revenue and accurate reporting of their perceived loan risk when assigning ratings. We conduct counterfactual experiments to answer the following substantive questions: (i) How does regulatory tightening or loosening impact Prosper’s revenue and truthful reporting of loan risk? (ii) What is the value of adaptive learning for Prosper? (iii) Is there any potential for Prosper to improve its current adaptive learning algorithm?

Keywords: Adaptive Learning, Generalized Revealed Preference, Concept Drift, Peer-to-peer Lending, Fintech

JEL Classification: C33, C35, C38, C53, C55, D12, D14, D22, G21