Search Results
Showing results 1 to 7 of approximately 7.
(refine search)
Working Paper
How Much Does Racial Bias Affect Mortgage Lending? Evidence from Human and Algorithmic Credit Decisions
We assess racial discrimination in mortgage approvals using new 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 race-blind 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 ...
Discussion Paper
Fair lending analysis of credit cards
This paper discusses some of the key fair lending risks that can arise in various stages of the marketing, acquisition, and management of credit card accounts, and the analysis that can be employed to manage such risks. The Equal Credit Opportunity Act (ECOA) and its implementing Regulation B prohibit discrimination in all aspects of credit transactions and include specific provisions relating to processes that employ credit scoring models. This paper discusses some of the areas of credit card operations that may be assessed in an effort to manage the risk of noncompliance with fair lending ...
Working Paper
Technological Innovation and Discrimination in Household Finance
Technology has changed how discrimination manifests itself in financial services. Replacing human discretion with algorithms in decision-making roles reduces taste-based discrimination, and new modeling techniques have expanded access to financial services to households who were previously excluded from these markets. However, algorithms can exhibit bias from human involvement in the development process, and their opacity and complexity can facilitate statistical discrimination inconsistent with antidiscrimination laws in several aspects of financial services provision, including advertising, ...
Working Paper
How Much Does Racial Bias Affect Mortgage Lending? Evidence from Human and Algorithmic Credit Decisions
We assess racial discrimination in mortgage approvals using new 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 race-blind 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 ...
Working Paper
How Much Does Racial Bias Affect Mortgage Lending? Evidence from Human and Algorithmic Credit Decisions
We assess racial discrimination in mortgage approvals using new 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 race-blind 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 ...
Working Paper
Do Minorities Pay More for Mortgages?
We test for racial discrimination in the prices charged by mortgage lenders. We construct a unique dataset where we observe all three dimensions of a mortgage's price: the interest rate, discount points, and fees. While we find statistically significant gaps by race and ethnicity in interest rates, these gaps are offset by differences in discount points. We trace out point-rate schedules and show that minorities and whites face identical schedules, but sort to different locations on the schedule. Such sorting may reflect systematic differences in liquidity or preferences. Finally, we find no ...
Working Paper
How Much Does Racial Bias Affect Mortgage Lending? Evidence from Human and Algorithmic Credit Decisions
We assess racial discrimination in mortgage approvals using new 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 race-blind 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 ...