One Threshold Doesn't Fit All: Tailoring Machine Learning Predictions of Consumer Default for Lower-Income Areas

54 Pages Posted: 22 Nov 2022

See all articles by Vitaly Meursault

Vitaly Meursault

Federal Reserve Banks - Federal Reserve Bank of Philadelphia

Daniel Moulton

Federal Reserve Banks - Federal Reserve Bank of Philadelphia

Larry Santucci

Federal Reserve Bank of Philadelphia

Nathan Schor

Federal Reserve Banks - Federal Reserve Bank of Philadelphia

Date Written: November 1, 2022

Abstract

Modeling advances create credit scores that predict default better overall, but raise concerns about their effect on protected groups. Focusing on low- and moderate-income (LMI) areas, we use an approach from the Fairness in Machine Learning literature — fairness constraints via group-specific prediction thresholds — and show that gaps in true positive rates (% of non-defaulters identified by the model as such) can be significantly reduced if separate thresholds can be chosen for non-LMI and LMI tracts. However, the reduction isn’t free as more defaulters are classified as good risks, potentially affecting both consumers’ welfare and lenders’ profits. The trade-offs become more favorable if the introduction of fairness constraints is paired with the introduction of more sophisticated models, suggesting a way forward. Overall, our results highlight the potential benefits of explicitly considering sensitive attributes in the design of loan approval policies and the potential benefits of output-based approaches to fairness in lending.

Keywords: Credit Scores, Group Disparities, Machine Learning, Fairness

JEL Classification: G51, C38, C53

Suggested Citation

Meursault, Vitaly and Moulton, Daniel and Santucci, Larry and Schor, Nathan, One Threshold Doesn't Fit All: Tailoring Machine Learning Predictions of Consumer Default for Lower-Income Areas (November 1, 2022). FRB of Philadelphia Working Paper No. 22-39, Available at SSRN: https://ssrn.com/abstract=4283403 or http://dx.doi.org/10.21799/frbp.wp.2022.39

Vitaly Meursault (Contact Author)

Federal Reserve Banks - Federal Reserve Bank of Philadelphia ( email )

Ten Independence Mall
Philadelphia, PA 19106-1574
United States

Daniel Moulton

Federal Reserve Banks - Federal Reserve Bank of Philadelphia ( email )

Ten Independence Mall
Philadelphia, PA 19106-1574
United States

Larry Santucci

Federal Reserve Bank of Philadelphia ( email )

Ten Independence Mall
Philadelphia, PA 19106-1574
United States
2155746014 (Phone)

HOME PAGE: http://https://www.philadelphiafed.org/our-people/larry-santucci

Nathan Schor

Federal Reserve Banks - Federal Reserve Bank of Philadelphia ( email )

Ten Independence Mall
Philadelphia, PA 19106-1574
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
7
Abstract Views
47
PlumX Metrics