Generative AI and the Evolution of Mortgage Underwriting: Measuring and Mitigating Racial Disparities

Abstract Mortgage underwriting is entering a new phase of technological change as general-purpose generative AI tools begin to appear in mortgage origination workflows. We develop an audit framework to evaluate how large language models process mortgage applications. Using real HMDA applications, we experimentally manipulate borrower race, race proxies, and credit quality, and prompt leading commercial LLMs to make approval and pricing recommendations. LLMs recommend more denials and higher interest rates for Black applicants than otherwise identical white applicants, with disparities largest for riskier loans and persisting when race is signaled through names or locations. A simple instruction to avoid bias substantially reduces disparities when race is explicit, partially reduces the name-based pricing gap, and does little against the geographic pricing gap. In matched HMDA–Freddie Mac data, race-blind LLM recommendations correlate with actual lender pricing and subsequent delinquency, though the delinquency association operates largely through observed credit scores. The results show how AI auditing can inform mortgage underwriting governance before general-purpose models become more deeply embedded in origination workflows.

Authors

Institutions

Publication Details

Journal
The Journal of Real Estate Finance and Economics
Published
2026-11-14
DOI
https://doi.org/10.1007/s11146-026-10085-4
Citations
25
Primary Topic
Ethics and Social Impacts of AI
Type
article
Field-Weighted Citation Impact
12.98

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Generative AI and the Evolution of Mortgage Underwriting: Measuring and Mitigating Racial Disparities

S. McKay Price, Donald E. Bowen, Ke Yang, Luke C.D. Stein
25 citations
The Journal of Real Estate Finance and Economics
Ethics and Social Impacts of AI
12.98
article

Generative AI and the Evolution of Mortgage Underwriting: Measuring and Mitigating Racial Disparities

S. McKay Price, Donald E. Bowen, Ke Yang, Luke C.D. Stein
article en
25 citations

Abstract

Abstract Mortgage underwriting is entering a new phase of technological change as general-purpose generative AI tools begin to appear in mortgage origination workflows. We develop an audit framework to evaluate how large language models process mortgage applications. Using real HMDA applications, we experimentally manipulate borrower race, race proxies, and credit quality, and prompt leading commercial LLMs to make approval and pricing recommendations. LLMs recommend more denials and higher interest rates for Black applicants than otherwise identical white applicants, with disparities largest for riskier loans and persisting when race is signaled through names or locations. A simple instruction to avoid bias substantially reduces disparities when race is explicit, partially reduces the name-based pricing gap, and does little against the geographic pricing gap. In matched HMDA–Freddie Mac data, race-blind LLM recommendations correlate with actual lender pricing and subsequent delinquency, though the delinquency association operates largely through observed credit scores. The results show how AI auditing can inform mortgage underwriting governance before general-purpose models become more deeply embedded in origination workflows.

The Journal of Real Estate Finance and Economics
Lehigh University (US), Babson College (US)
University of Oklahoma, Lehigh University, Northern Kentucky University, University of Cambridge, Universiteit van Amsterdam, Concordia University
Reduced inequalities
Openalex Percentile: Top 1%
Ethics and Social Impacts of AI
12.98
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon