Credit Scores: Performance and Equity

TL;DR

This work benchmarks a widely used credit score against a machine learning model of consumer default and finds significant misclassification of borrowers, especially those with low scores, suggesting that improving credit scoring performance could lead to more equitable access to credit.

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.

Figures (7)

• Figure 1: Gini Coefficient, Credit Score and Prediction Model
• Figure 2: Performance by Feature Composition
• Figure 3: Credit Score Histogram by Years
• Figure 4: Gini Coefficient and Rank Correlation with Realized Default Rate
• Figure 5: Credit Bureau & HMDA trends (part 1).