Premium
Predictably Unequal? The Effects of Machine Learning on Credit Markets
Author(s) -
FUSTER ANDREAS,
GOLDSMITHPINKHAM PAUL,
RAMADORAI TARUN,
WALTHER ANSGAR
Publication year - 2022
Publication title -
the journal of finance
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 18.151
H-Index - 299
eISSN - 1540-6261
pISSN - 0022-1082
DOI - 10.1111/jofi.13090
Subject(s) - flexibility (engineering) , statistical learning , statistical discrimination , econometrics , machine learning , artificial intelligence , simple (philosophy) , computer science , race (biology) , economics , statistics , mathematics , demographic economics , sociology , gender studies , philosophy , epistemology
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.