Working Paper

How Much Does Racial Bias Affect Mortgage Lending? Evidence from Human and Algorithmic Credit Decisions

Abstract: We assess racial discrimination in mortgage approvals using confidential data on mortgage applications. Minority applicants tend to have significantly lower credit scores, higher leverage, and are less likely than White applicants to receive algorithmic approval from raceblind government-automated underwriting systems (AUS). Observable applicant-risk factors explain most of the racial disparities in lender denials. Further, we exploit the AUS data to show there are risk factors we do not directly observe, and our analysis indicates that these factors explain at least some of the residual 1-2 percentage point denial gaps. Overall, we find that differential treatment has played a more limited role in generating denial disparities in recent years than suggested by previous research.

Keywords: mortgage; mortgage approval; discrimination; mortgage lender; automated underwriting; credit score; fair lending;

JEL Classification: G21; G28; R30; R51;

https://doi.org/10.21799/frbp.wp.2024.09

Bibliographic Information

Provider: Federal Reserve Bank of Philadelphia

Part of Series: Working Papers

Publication Date: 2024-03-07

Number: 24-09