IDEAS home Printed from https://ideas.repec.org/a/wly/jpamgt/v44y2025i3p792-815.html
   My bibliography  Save this article

One threshold doesn't fit all: Tailoring machine learning predictions of consumer default for lower‐income areas

Author

Listed:
  • Vitaly Meursault
  • Daniel Moulton
  • Larry Santucci
  • Nathan Schor

Abstract

Improving fairness across policy domains often comes at a cost. However, as machine learning (ML) advances lead to more accurate predictive models in fields like lending, education, healthcare, and criminal justice, policymakers may find themselves better positioned to implement effective fairness measures. Using credit bureau data and ML, we show that setting different lending thresholds for low‐ and moderate‐income (LMI) neighborhoods relative to non‐LMI neighborhoods can equalize the rate at which equally creditworthy borrowers receive credit. ML models alone better identify creditworthy individuals in all groups but remain more accurate for the majority group. A policy that equalizes access via separate thresholds imposes a cost on lenders, but this cost is outweighed by the substantial gains from ML. This approach aligns with the motivation behind existing laws such as the Community Reinvestment Act, which encourages lenders to meet the credit needs of underserved communities. Targeted Special Purpose Credit Programs could provide the opportunity to prototype and test these ideas in the field.

Suggested Citation

  • Vitaly Meursault & Daniel Moulton & Larry Santucci & Nathan Schor, 2025. "One threshold doesn't fit all: Tailoring machine learning predictions of consumer default for lower‐income areas," Journal of Policy Analysis and Management, John Wiley & Sons, Ltd., vol. 44(3), pages 792-815, June.
  • Handle: RePEc:wly:jpamgt:v:44:y:2025:i:3:p:792-815
    DOI: 10.1002/pam.22662
    as

    Download full text from publisher

    File URL: https://doi.org/10.1002/pam.22662
    Download Restriction: no

    File URL: https://libkey.io/10.1002/pam.22662?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    Other versions of this item:

    References listed on IDEAS

    as
    1. Stefania Albanesi & Domonkos F. Vamossy, 2019. "Predicting Consumer Default: A Deep Learning Approach," NBER Working Papers 26165, National Bureau of Economic Research, Inc.
    2. Mikhed, Vyacheslav & Vogan, Michael, 2018. "How data breaches affect consumer credit," Journal of Banking & Finance, Elsevier, vol. 88(C), pages 192-207.
    3. Laura Blattner & Scott Nelson, 2021. "How Costly is Noise? Data and Disparities in Consumer Credit," Papers 2105.07554, arXiv.org.
    4. Robert B. Avery & Kenneth P. Brevoort & Glenn Canner, 2012. "Does Credit Scoring Produce a Disparate Impact?," Real Estate Economics, American Real Estate and Urban Economics Association, vol. 40, pages 65-114, December.
    5. Blattner, Laura & Nelson, Scott, 2021. "How Costly Is Noise? Data and Disparities in Consumer Credit," Research Papers 3978, Stanford University, Graduate School of Business.
    6. Friedman, Jerome H. & Hastie, Trevor & Tibshirani, Rob, 2010. "Regularization Paths for Generalized Linear Models via Coordinate Descent," Journal of Statistical Software, Foundation for Open Access Statistics, vol. 33(i01).
    7. Dubravka Ritter & David Skanderson, 2014. "Fair lending analysis of credit cards," Consumer Finance Institute discussion papers 14-2, Federal Reserve Bank of Philadelphia.
    8. Robert B. Avery & Paul S. Calem & Glenn B. Canner, 2003. "An overview of consumer data and credit reporting," Federal Reserve Bulletin, Board of Governors of the Federal Reserve System (U.S.), vol. 89(Feb), pages 47-73, February.
    9. Donghoon Lee & Wilbert Van der Klaauw, 2010. "An introduction to the FRBNY Consumer Credit Panel," Staff Reports 479, Federal Reserve Bank of New York.
    10. Talia Gillis & Bryce McLaughlin & Jann Spiess, 2021. "On the Fairness of Machine-Assisted Human Decisions," Papers 2110.15310, arXiv.org, revised Sep 2023.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Stefania Albanesi & Domonkos F. Vamossy, 2024. "Credit Scores: Performance and Equity," NBER Working Papers 32917, National Bureau of Economic Research, Inc.
    2. Christa Gibbs & Benedict Guttman-Kenney & Donghoon Lee & Scott Nelson & Wilbert van der Klaauw & Jialan Wang, 2025. "Consumer Credit Reporting Data," Journal of Economic Literature, American Economic Association, vol. 63(2), pages 598-636, June.
    3. Subhadeep Mukhopadhyay, 2021. "InfoGram and Admissible Machine Learning," Papers 2108.07380, arXiv.org, revised Aug 2021.
    4. Stefania Albanesi, 2025. "Comment on "Credit Scores and Inequality Across the Life Cycle"," NBER Chapters, in: NBER Macroeconomics Annual 2025, volume 40, National Bureau of Economic Research, Inc.
    5. Will Dobbie & Paul Goldsmith‐Pinkham & Neale Mahoney & Jae Song, 2020. "Bad Credit, No Problem? Credit and Labor Market Consequences of Bad Credit Reports," Journal of Finance, American Finance Association, vol. 75(5), pages 2377-2419, October.
    6. David Horneber & Sven Laumer, 2023. "Algorithmic Accountability," Business & Information Systems Engineering: The International Journal of WIRTSCHAFTSINFORMATIK, Springer;Gesellschaft für Informatik e.V. (GI), vol. 65(6), pages 723-730, December.
    7. John Eric Humphries & Nicholas Mader & Daniel Tannenbaum & Winnie van Dijk, 2019. "Does Eviction Cause Poverty? Quasi-Experimental Evidence from Cook County, IL," CESifo Working Paper Series 7800, CESifo.
    8. Paul Goldsmith-Pinkham & Maxim L. Pinkovskiy & Jacob Wallace, 2020. "The Great Equalizer: Medicare and the Geography of Consumer Financial Strain," Staff Reports 911, Federal Reserve Bank of New York.
    9. Olivier Armantier & Sebastian Doerr & Jon Frost & Andreas Fuster & Kelly Shue, 2024. "Nothing to hide? Gender and age differences in willingness to share data," Swiss Finance Institute Research Paper Series 24-99, Swiss Finance Institute.
    10. Paul Goldsmith-Pinkham & Maxim Pinkovskiy & Jacob Wallace, 2020. "Medicare and the Geography of Financial Health," Working Papers 2020-004, Human Capital and Economic Opportunity Working Group.
    11. Hurtado, Agustin & Sakong, Jung, 2022. "The effect of minority bank ownership on minority credit," Working Papers 325, The University of Chicago Booth School of Business, George J. Stigler Center for the Study of the Economy and the State.
    12. Sabrina T. Howell & Theresa Kuchler & David Snitkof & Johannes Stroebel & Jun Wong, 2024. "Lender Automation and Racial Disparities in Credit Access," Journal of Finance, American Finance Association, vol. 79(2), pages 1457-1512, April.
    13. Valentina Dimitrova-Grajzl & Peter Grajzl & A. Joseph Guse & Richard M. Todd & Michael Williams, 2018. "Neighborhood Racial Characteristics, Credit History, and Bankcard Credit in Indian Country," Comparative Economic Studies, Palgrave Macmillan;Association for Comparative Economic Studies, vol. 60(3), pages 410-441, September.
    14. Ryan M. Goodstein & Alicia Lloro & Sherrie L.W. Rhine & Jeffrey M. Weinstein, 2021. "What accounts for racial and ethnic differences in credit use?," Journal of Consumer Affairs, Wiley Blackwell, vol. 55(2), pages 389-416, June.
    15. Eglė Jakučionytė & Swapnil Singh, 2023. "Emergence of subprime lending in minority neighborhoods," Real Estate Economics, American Real Estate and Urban Economics Association, vol. 51(6), pages 1547-1583, November.
    16. Ballance, Joshua & Clifford, Robert & Shoag, Daniel, 2020. "“No more credit score”: Employer credit check bans and signal substitution," Labour Economics, Elsevier, vol. 63(C).
    17. Ströbel, Johannes & Howell, Sabrina & Kuchler, Theresa & Snitkof, David, 2021. "Racial Disparities in Access to Small Business Credit: Evidence from the Paycheck Protection Program," CEPR Discussion Papers 16623, C.E.P.R. Discussion Papers.
    18. Greenwald, Daniel L. & Howell, Sabrina T. & Li, Cangyuan & Yimfor, Emmanuel, 2024. "Regulatory arbitrage or random errors? Implications of race prediction algorithms in fair lending analysis," Journal of Financial Economics, Elsevier, vol. 157(C).
    19. Cusato, Antonio & Castillo, José Luis & IDB Invest, 2023. "Access to Credit and the Expansion of Broadband Internet in Peru," IDB Publications (Working Papers) 12922, Inter-American Development Bank.
    20. Langenbucher, Katja, 2022. "Consumer credit in the age of AI: Beyond anti-discrimination law," LawFin Working Paper Series 42, Goethe University, Center for Advanced Studies on the Foundations of Law and Finance (LawFin).

    More about this item

    JEL classification:

    • G51 - Financial Economics - - Household Finance - - - Household Savings, Borrowing, Debt, and Wealth
    • C38 - Mathematical and Quantitative Methods - - Multiple or Simultaneous Equation Models; Multiple Variables - - - Classification Methdos; Cluster Analysis; Principal Components; Factor Analysis
    • C53 - Mathematical and Quantitative Methods - - Econometric Modeling - - - Forecasting and Prediction Models; Simulation Methods

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:wly:jpamgt:v:44:y:2025:i:3:p:792-815. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Wiley Content Delivery (email available below). General contact details of provider: http://www3.interscience.wiley.com/journal/34787/home .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.