Credit Scores: Performance and Equity

TL;DR

This paper evaluates the performance of traditional credit scores versus machine learning models, revealing significant misclassification issues and demonstrating that ML models can improve predictive accuracy for underserved groups, promoting equity in credit access.

Contribution

The study benchmarks traditional credit scores against machine learning models, showing ML's potential to enhance accuracy and fairness in credit decision-making.

Findings

Traditional scores misclassify many low-score borrowers.

ML models improve prediction for young, low-income, minority groups.

Better scoring models could lead to more equitable credit access.

Abstract

Credit scores are critical for allocating consumer debt in the United States, yet little evidence is available on their performance. We benchmark a widely used credit score against a machine learning model of consumer default and find significant misclassification of borrowers, especially those with low scores. Our model improves predictive accuracy for young, low-income, and minority groups due to its superior performance with low quality data, resulting in a gain in standing for these populations. Our findings suggest that improving credit scoring performance could lead to more equitable access to credit.