IDEAS home Printed from
   My bibliography  Save this paper

One Threshold Doesn’t Fit All: Tailoring Machine Learning Predictions of Consumer Default for Lower-Income Areas




Modeling advances create credit scores that predict default better overall, but raise concerns about their effect on protected groups. Focusing on low- and moderate-income (LMI) areas, we use an approach from the Fairness in Machine Learning literature — fairness constraints via group-specific prediction thresholds — and show that gaps in true positive rates (% of non-defaulters identified by the model as such) can be significantly reduced if separate thresholds can be chosen for non-LMI and LMI tracts. However, the reduction isn’t free as more defaulters are classified as good risks, potentially affecting both consumers’ welfare and lenders’ profits. The trade-offs become more favorable if the introduction of fairness constraints is paired with the introduction of more sophisticated models, suggesting a way forward. Overall, our results highlight the potential benefits of explicitly considering sensitive attributes in the design of loan approval policies and the potential benefits of output-based approaches to fairness in lending.

Suggested Citation

  • Vitaly Meursault & Daniel Moulton & Larry Santucci & Nathan Schor, 2022. "One Threshold Doesn’t Fit All: Tailoring Machine Learning Predictions of Consumer Default for Lower-Income Areas," Working Papers 22-39, Federal Reserve Bank of Philadelphia.
  • Handle: RePEc:fip:fedpwp:95158
    DOI: 10.21799/frbp.wp.2022.39

    Download full text from publisher

    File URL:
    Download Restriction: no

    File URL:
    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

    References listed on IDEAS

    1. Laura Blattner & Scott Nelson, 2021. "How Costly is Noise? Data and Disparities in Consumer Credit," Papers 2105.07554,
    2. 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.
    3. Stefania Albanesi & Domonkos F. Vamossy, 2019. "Predicting Consumer Default: A Deep Learning Approach," Working Papers 2019-056, Human Capital and Economic Opportunity Working Group.
    4. Blattner, Laura & Nelson, Scott, 2021. "How Costly Is Noise? Data and Disparities in Consumer Credit," Research Papers 3978, Stanford University, Graduate School of Business.
    5. 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).
    6. Mikhed, Vyacheslav & Vogan, Michael, 2018. "How data breaches affect consumer credit," Journal of Banking & Finance, Elsevier, vol. 88(C), pages 192-207.
    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. Talia Gillis & Bryce McLaughlin & Jann Spiess, 2021. "On the Fairness of Machine-Assisted Human Decisions," Papers 2110.15310,
    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. Subhadeep Mukhopadhyay, 2021. "InfoGram and Admissible Machine Learning," Papers 2108.07380,, revised Aug 2021.
    2. Egle Jakucionyte & Swapnil Singh, 2021. "Emergence of Subprime Lending in Minority Neighborhoods," Bank of Lithuania Working Paper Series 94, Bank of Lithuania.
    3. 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.
    4. Sabrina T. Howell & Theresa Kuchler & David Snitkof & Johannes Stroebel & Jun Wong, 2021. "Lender Automation and Racial Disparities in Credit Access," NBER Working Papers 29364, National Bureau of Economic Research, Inc.
    5. Sabrina T. Howell & Theresa Kuchler & David Snitkof & Johannes Stroebel & Jun Wong, 2021. "Racial Disparities in Access to Small Business Credit: Evidence from the Paycheck Protection Program," CESifo Working Paper Series 9345, CESifo.
    6. 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.
    7. Tutz, Gerhard & Pößnecker, Wolfgang & Uhlmann, Lorenz, 2015. "Variable selection in general multinomial logit models," Computational Statistics & Data Analysis, Elsevier, vol. 82(C), pages 207-222.
    8. Ernesto Carrella & Richard M. Bailey & Jens Koed Madsen, 2018. "Indirect inference through prediction," Papers 1807.01579,
    9. Rui Wang & Naihua Xiu & Kim-Chuan Toh, 2021. "Subspace quadratic regularization method for group sparse multinomial logistic regression," Computational Optimization and Applications, Springer, vol. 79(3), pages 531-559, July.
    10. Mkhadri, Abdallah & Ouhourane, Mohamed, 2013. "An extended variable inclusion and shrinkage algorithm for correlated variables," Computational Statistics & Data Analysis, Elsevier, vol. 57(1), pages 631-644.
    11. Masakazu Higuchi & Mitsuteru Nakamura & Shuji Shinohara & Yasuhiro Omiya & Takeshi Takano & Daisuke Mizuguchi & Noriaki Sonota & Hiroyuki Toda & Taku Saito & Mirai So & Eiji Takayama & Hiroo Terashi &, 2022. "Detection of Major Depressive Disorder Based on a Combination of Voice Features: An Exploratory Approach," IJERPH, MDPI, vol. 19(18), pages 1-13, September.
    12. Susan Athey & Guido W. Imbens & Stefan Wager, 2018. "Approximate residual balancing: debiased inference of average treatment effects in high dimensions," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 80(4), pages 597-623, September.
    13. Vincent, Martin & Hansen, Niels Richard, 2014. "Sparse group lasso and high dimensional multinomial classification," Computational Statistics & Data Analysis, Elsevier, vol. 71(C), pages 771-786.
    14. Chen, Le-Yu & Lee, Sokbae, 2018. "Best subset binary prediction," Journal of Econometrics, Elsevier, vol. 206(1), pages 39-56.
    15. Perrot-Dockès Marie & Lévy-Leduc Céline & Chiquet Julien & Sansonnet Laure & Brégère Margaux & Étienne Marie-Pierre & Robin Stéphane & Genta-Jouve Grégory, 2018. "A variable selection approach in the multivariate linear model: an application to LC-MS metabolomics data," Statistical Applications in Genetics and Molecular Biology, De Gruyter, vol. 17(5), pages 1-14, October.
    16. Fan, Jianqing & Jiang, Bai & Sun, Qiang, 2022. "Bayesian factor-adjusted sparse regression," Journal of Econometrics, Elsevier, vol. 230(1), pages 3-19.
    17. Jun Li & Serguei Netessine & Sergei Koulayev, 2018. "Price to Compete … with Many: How to Identify Price Competition in High-Dimensional Space," Management Science, INFORMS, vol. 64(9), pages 4118-4136, September.
    18. Sung Jae Jun & Sokbae Lee, 2020. "Causal Inference under Outcome-Based Sampling with Monotonicity Assumptions," Papers 2004.08318,, revised Nov 2021.
    19. Rina Friedberg & Julie Tibshirani & Susan Athey & Stefan Wager, 2018. "Local Linear Forests," Papers 1807.11408,, revised Sep 2020.
    20. Xiangwei Li & Thomas Delerue & Ben Schöttker & Bernd Holleczek & Eva Grill & Annette Peters & Melanie Waldenberger & Barbara Thorand & Hermann Brenner, 2022. "Derivation and validation of an epigenetic frailty risk score in population-based cohorts of older adults," Nature Communications, Nature, vol. 13(1), pages 1-11, December.

    More about this item


    Credit Scores; Group Disparities; Machine Learning; Fairness;
    All these keywords.

    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


    Access and download statistics


    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:fip:fedpwp:95158. See general information about how to correct material in RePEc.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: . General contact details of provider: .

    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: Beth Paul (email available below). General contact details of provider: .

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

    IDEAS is a RePEc service hosted by the Research Division of the Federal Reserve Bank of St. Louis . RePEc uses bibliographic data supplied by the respective publishers.