Predictably Unequal? The Effects of Machine Learning on Credit Markets

Innovations in statistical technology in functions including credit-screening have raised concerns about distributional impacts across categories such as race. Theoretically, distributional effects of better statistical technology can come from greater flexibility to uncover structural relationships or from triangulation of otherwise excluded characteristics. Using data on U.S. mortgages, we predict default using traditional and machine learning models. We find that Black and Hispanic borrowers are disproportionately less likely to gain from the introduction of machine learning. In a simple equilibrium credit market model, machine learning increases disparity in rates between and within groups, with these changes attributable primarily to greater flexibility.

Automated summary

Innovations in statistical technology, particularly in credit-screening, have raised concerns about the distributional impacts across race categories. Using traditional and machine learning models on U.S. mortgage data, it was found that Black and Hispanic borrowers did not benefit proportionately from machine learning, leading to increased disparities in interest rates. This disparity was primarily attributed to the greater flexibility of machine learning models.