Actions Speak Louder than Words : Imputing Users’ Reputation from Transaction History

Choice of market mechanism is a key for success for any online marketplace. In recent years, as P2P lending has seen phenomenal growth, leading P2P lending platforms have used various market mechanisms, and in some cases, switched from one mechanism to another, chasing higher market share and overall growth. While Prosper.com, a leading P2P lending platform has switched from auction lending model to fixed price lending model, recent studies show that overall social welfare was higher with the auction lending model. However, the success of auction lending model hinges on lenders' ability to assess the credit risk of the borrowers. Building on extant literature and in support of the auction lending model to increase the social welfare, we design an artifact to dynamically estimate borrowers' reputation to level the playing field and improve the allocative efficiency in P2P lending markets. We posit that borrowers' reputation built on transactional data, readily available on P2P lending platforms, represents the collective perception of lenders about the borrowers. We propose a dynamic latent class model of reputation, and use the latent instrumental variable approach to deal with endogeneity. We test our artifact using real-world P2P lending data. We show that accounting for reputation improves the explanatory power of the model, and provides a way to empirically model the evolution and impact of reputation in online platforms where repeated transactions are performed