Predictably Unequal? The Effects of Machine Learning on Credit Markets
Open accessThe DOI matches its Crossref record; 77 of the 78 references it cites were found in a registry or an index, and 1 are not checked yet.
Abstract
Innovations in statistical technology, including in predicting creditworthiness, have sparked concerns about distributional impacts across categories such as race. Theoretically, distributional consequences of better statistical technology can come from greater flexibility to uncover structural relationships, or from triangulation of otherwise excluded characteristics. Using data on US mortgages, we predict default using traditional and machine learning models. We find that Black and Hispanic borrowers are disproportionately less likely to gain from the introduction of machine learning. In a simple equilibrium credit market model, machine learning increases disparity in rates between and within groups; these changes are primarily attributable to greater flexibility.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Unfortunately, even if protections for specific classes can be encoded in an algorithm, there could always be biases that were not considered ex ante, as in the case, for example, of language models reproducing heavily male-focused texts (Fuster et al. 2017;Doshi-Velez and Kim 2017).”
From The ethics of algorithms: key problems and solutions (2022) · cites this paper as Fuster et al. 2017
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · cited 5×
“We estimate a set of increasingly sophisticated statistical models, beginning with a simple logistic regression of default outcomes on borrower and loan characteristics, and culminating in a random forest machine learning model (Ho, 1998; Breiman, 2001).”
InfluentialXGBoost: A Scalable Tree Boosting System
Chen, T., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939785 · Cited by 54,569 · cited 5×
“6We also employ the eXtreme Gradient Boosting (XGBoost) model (Chen and Guestrin, 2016), which delivers very similar results to the Random Forest.”
InfluentialThe Elements of Statistical Learning
Hastie, T., Tibshirani, R., & Friedman, J. (2009) · Springer Series in Statistics · doi:10.1007/978-0-387-84858-7 · Cited by 25,970
The Elements of Statistical Learning
Hastie, T., Friedman, J., & Tibshirani, R. (2001) · Springer Series in Statistics · doi:10.1007/978-0-387-21606-5 · Cited by 24,162
An Introduction to Statistical Learning
James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013) · Springer Texts in Statistics · doi:10.1007/978-1-4614-7138-7 · Cited by 12,106
The use of the area under the ROC curve in the evaluation of machine learning algorithms
Bradley, A. P. (1997) · Pattern Recognition · doi:10.1016/s0031-3203(96)00142-2 · Cited by 7,217 · cited 9×
“For the origination vintages from 2009-2013, our HMDA-McDash dataset corresponds to 45% of all loans in HMDA. This fraction is driven by the coverage of McDash (corresponding to 73% of HMDA originations over this period) and the share of these McDash loans that can be uniquely matched to the HMDA loans (just over 60%)…”
InfluentialThe random subspace method for constructing decision forests
Ho, T. K. (1998) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.709601 · Cited by 6,842 · cited 3×
“We estimate a set of increasingly sophisticated statistical models, beginning with a simple logistic regression of default outcomes on borrower and loan characteristics, and culminating in a random forest machine learning model (Ho, 1998; Breiman, 2001).”
BackgroundMethodInfluentialThe relationship between Precision-Recall and ROC curves
Davis, J., & Goadrich, M. (2006) · Proceedings of the 23rd international conference on Machine learning - ICML '06 · doi:10.1145/1143844.1143874 · Cited by 6,559 · cited 2×
“, Einav and Finkelstein (2011), Chetty and Finkelstein (2013), Bundorf et al.”
An overview of statistical learning theory
Vapnik, V. N. (1999) · IEEE Transactions on Neural Networks · doi:10.1109/72.788640 · Cited by 6,266
Time Series: Theory and Methods
Ziegel, E. R., Brockwell, P., & Davis, R. (1992) · Technometrics · doi:10.2307/1270070 · Cited by 5,012
Research works printed but not linked: 5
- Ajay Agrawal, 2018, Prediction Machines: The Simple Economics of Artificial Intelligence
- Cov, = 0 for a mean-zero normal variable, and residual ? z = z ? E[z]. By the Frisch-WaughLovell theorem, the coefficient on x 2 in?Pin? in?P quad (x) is the same as in the regression of ? y on ? z
- Tianqi Chen, 2016, XGBoost: A Scalable Tree Boosting System, Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785, 10.1145/2939672.2939785 · DOI · Paper page
- Andrew K Feigenberg, 1993, A new default benchmark for pricing nonagency securities
- Andreas Fuster, 2013, The Rising Gap between Primary and Secondary Mortgage Rates, Federal Reserve Bank of, New York Economic Policy Review, 19, 17
Cited by
Artificial intelligence, firm growth, and product innovation
Babina, T., Fedyk, A., He, A., & Hodson, J. (2024) · Journal of Financial Economics · doi:10.1016/j.jfineco.2023.103745 · Cited by 1,460
The Role of Technology in Mortgage Lending
Fuster, A., Plosser, M., Schnabl, P., & Vickery, J. (2019) · The Review of Financial Studies · doi:10.1093/rfs/hhz018 · Cited by 1,128
Self-citationOn the Rise of FinTechs: Credit Scoring Using Digital Footprints
Berg, T., Burg, V., Gombović, A., & Puri, M. (2020) · The Review of Financial Studies · doi:10.1093/rfs/hhz099 · Cited by 919
Algorithmic Fairness: Choices, Assumptions, and Definitions
Mitchell, S., Potash, E., Barocas, S., D'Amour, A., & Lum, K. (2021) · Annual Review of Statistics and Its Application · doi:10.1146/annurev-statistics-042720-125902 · Cited by 687
Consumer-lending discrimination in the FinTech Era
Bartlett, R., Morse, A., Stanton, R., & Wallace, N. (2022) · Journal of Financial Economics · doi:10.1016/j.jfineco.2021.05.047 · Cited by 659
“However, as discussed above, Fuster et al. (2019) conclude that selection is unlikely to be a major”
Metadata
- Authors
- Fuster, A., Goldsmith-Pinkham, P. S., Ramadorai, T., & Walther, A.
- Venue
- The Journal of Finance
- Publisher
- Elsevier BV
- Published
- 2017
- Volume
- 77
- Issue
- 1
- Pages
- 5-47
- ISSN
- 0022-1082 (ISSN-L)
- OpenAlex
- W3209809080
- Cited by
- 769
- References
- 65
- Citations by year
- 2026: 198 · 2025: 144 · 2024: 87 · 2023: 108 · 2022: 62 · 2021: 68 · 2020: 61 · 2019: 23 · 2018: 16 · 2017: 1
- FWCI
- 101.59
- Type
- journal article
- Language
- en
- Open access
- green
- doi.org
- Locations
- The Journal of Finance (publishedVersion)
- SSRN Electronic Journal (acceptedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- Infoscience (Ecole Polytechnique Fédérale de Lausanne) (submittedVersion, cc-by-nc-nd)
- Spiral (Imperial College London) (submittedVersion)
- Zurich Open Repository and Archive (University of Zurich) (submittedVersion, other-oa)
- Zurich Open Repository and Archive (University of Zurich)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Social Sciences › Business, Management and Accounting › Accounting › Financial Distress and Bankruptcy Prediction
- Social Sciences › Sociology and Political Science › Urban, Neighborhood, and Segregation Studies
- Keywords
- machine learning, credit markets, mortgage lending, default prediction, racial disparities, algorithmic discrimination, credit scoring, Black borrowers, Hispanic borrowers, distributional effects
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.