Regulatory arbitrage or random errors? Implications of race prediction algorithms in fair lending analysis

Daniel L. Greenwald, Sabrina T. Howell, Cangyuan Li and Emmanuel Yimfor

Journal of Financial Economics, 2024, vol. 157, issue C

Abstract: When race is not directly observed, regulators and analysts commonly predict it using algorithms based on last name and address. In small business lending—where regulators assess fair lending law compliance using the Bayesian Improved Surname Geocoding (BISG) algorithm—we document large prediction errors among Black Americans. The errors bias measured racial disparities in loan approval rates downward by 43%, with greater bias for traditional vs. fintech lenders. Regulation using self-identified race would increase lending to Black borrowers, but also shift lending toward affluent areas because errors correlate with socioeconomics. Overall, using race proxies in policymaking and research presents challenges.

Keywords: Racial disparities; Disparate impact analysis; Race-conscious policies; Race prediction; Small business lending; BISG (search for similar items in EconPapers)
JEL-codes: C81 G21 G23 G28 J15 (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0304405X24000801
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:jfinec:v:157:y:2024:i:c:s0304405x24000801

DOI: 10.1016/j.jfineco.2024.103857

Access Statistics for this article

Journal of Financial Economics is currently edited by G. William Schwert

More articles in Journal of Financial Economics from Elsevier
Bibliographic data for series maintained by Catherine Liu ().