Debiasing Alternative Data for Credit Underwriting Using Causal Inference

TL;DR

This paper introduces a causal inference-based method to debias alternative data in credit scoring, aiming to improve model fairness and accuracy across racial groups while ensuring legal compliance.

Contribution

It presents a novel approach combining causal inference with supervised learning to debias alternative data for credit underwriting, with theoretical nondiscrimination guarantees.

Findings

Improved model accuracy across racial groups.

Theoretically robust nondiscrimination guarantees.

Effective debiasing of alternative data in credit scoring.

Abstract

Alternative data provides valuable insights for lenders to evaluate a borrower's creditworthiness, which could help expand credit access to underserved groups and lower costs for borrowers. But some forms of alternative data have historically been excluded from credit underwriting because it could act as an illegal proxy for a protected class like race or gender, causing redlining. We propose a method for applying causal inference to a supervised machine learning model to debias alternative data so that it might be used for credit underwriting. We demonstrate how our algorithm can be used against a public credit dataset to improve model accuracy across different racial groups, while providing theoretically robust nondiscrimination guarantees.