Predictably Unequal? The Effects of Machine Learning on Credit Markets
By Andreas Fuster, Paul Goldsmith-Pinkham, Tarun Ramadorai, Ansgar Walther. 2020
567 citations recorded by the source corpus.
Recent innovations in statistical technology, including in evaluating creditworthiness, have sparked concerns about impacts on the fairness of outcomes across categories such as race and gender. We build a simple equilibrium model of credit provision in which to evaluate such impacts. We find that as statistical technology changes, the effects on disparity depend on a combination of the changes in the functional form used to evaluate creditworthiness using underlying borrower characteristics and the cross-category distribution of these characteristics. Employing detailed data on US mortgages and applications, we predict default using a number of popular machine learning techniques, and embed these techniques in our equilibrium model to analyze both extensive margin (exclusion) and intensive margin (rates) impacts on disparity. We propose a basic measure of cross-category disparity, and find that the machine learning models perform worse on this measure than logit models, especially on the intensive margin. We discuss the implications of our findings for mortgage policy.
Subfields: Accounting, Economics and Econometrics, Finance
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Economics and Econometrics
In Finance
Citations in the corpus
- Characterizing Fairness Over the Set of Good Models Under Selective Labels (2021, background): “Algorithmic risk assessments are used to inform decisions in high-stakes settings such as health care, child welfare, criminal justice, consumer lending and hiring (Caruana et al., 2015; Chouldechova et al., 2018; Kleinberg et al., 2018; Fuster et al., 2020; Raghavan et al., 2020).”
- Economics, Fairness and Algorithmic Bias (2020, unknown): “Fuster et al. (2017) examine the effects of better statistical technology on lending using a structural model of both loan rates as well as decisions on loan applications in equilibrium.”
- Algorithmic bias: review, synthesis, and future research directions (2021, background): “Consequently, the algorithm will replicate and worse, reinforce the gender bias that might have previously led to biased loan decisions (Fuster et al., 2018).”
- Consumer-lending discrimination in the FinTech Era (2019, unknown): “However, as discussed above, Fuster et al. (2019) conclude that selection is unlikely to be a major”