Predictably Unequal? The Effects of Machine Learning on Credit Markets

92 Pages Posted: 17 Nov 2017 Last revised: 24 Jun 2021

See all articles by Andreas Fuster

Andreas Fuster

École Polytechnique Fédérale de Lausanne; Swiss Finance Institute; Centre for Economic Policy Research (CEPR)

Paul S. Goldsmith-Pinkham

Yale School of Management

Tarun Ramadorai

Imperial College London; Centre for Economic Policy Research (CEPR); European Corporate Governance Institute (ECGI)

Ansgar Walther

Imperial College London; Centre for Economic Policy Research (CEPR)

Multiple version iconThere are 2 versions of this paper

Date Written: June 21, 2021

Abstract

Innovations in statistical technology, including in predicting creditworthiness, have sparked concerns about distributional impacts across categories such as race. Theoretically, distributional consequences of better statistical technology can come from greater flexibility to uncover structural relationships, or from triangulation of otherwise excluded characteristics. Using data on US 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; these changes are primarily attributable to greater flexibility.

Keywords: machine learning, credit, mortgages, disparate impact, race

JEL Classification: G21, G28, G50, R30

Suggested Citation

Fuster, Andreas and Goldsmith-Pinkham, Paul S. and Ramadorai, Tarun and Walther, Ansgar, Predictably Unequal? The Effects of Machine Learning on Credit Markets (June 21, 2021). Journal of Finance, Forthcoming, Available at SSRN: https://ssrn.com/abstract=3072038 or http://dx.doi.org/10.2139/ssrn.3072038

Andreas Fuster

École Polytechnique Fédérale de Lausanne ( email )

Quartier UNIL-Chamberonne
Bâtiment Extranef
CH-1015 Lausanne
Switzerland

Swiss Finance Institute ( email )

c/o University of Geneva
40, Bd du Pont-d'Arve
CH-1211 Geneva 4
Switzerland

Centre for Economic Policy Research (CEPR) ( email )

London
United Kingdom

Paul S. Goldsmith-Pinkham

Yale School of Management ( email )

NY
United States

HOME PAGE: http://paulgp.github.io

Tarun Ramadorai (Contact Author)

Imperial College London ( email )

South Kensington Campus
Exhibition Road
London, Greater London SW7 2AZ
United Kingdom

HOME PAGE: http://www.tarunramadorai.com

Centre for Economic Policy Research (CEPR) ( email )

London
United Kingdom

European Corporate Governance Institute (ECGI) ( email )

c/o the Royal Academies of Belgium
Rue Ducale 1 Hertogsstraat
1000 Brussels
Belgium

Ansgar Walther

Imperial College London ( email )

South Kensington Campus
Exhibition Road
London, Greater London SW7 2AZ
United Kingdom

Centre for Economic Policy Research (CEPR) ( email )

London
United Kingdom

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
7,470
Abstract Views
26,181
Rank
1,689
PlumX Metrics