Fair Credit Scorer through Bayesian Approach

TL;DR

This paper introduces a Bayesian-based credit scoring model that aims to improve fairness by removing correlations between protected attributes and features, addressing bias in machine learning applications.

Contribution

It proposes a novel Bayesian approach with latent variables to eliminate bias related to protected attributes in credit scoring models.

Findings

Successfully reduces bias against sub-populations

Demonstrates improved fairness in credit predictions

Utilizes Bayesian methods for model estimation

Abstract

Machine learning currently plays an increasingly important role in people's lives in areas such as credit scoring, auto-driving, disease diagnosing, and insurance quoting. However, in many of these areas, machine learning models have performed unfair behaviors against some sub-populations, such as some particular groups of race, sex, and age. These unfair behaviors can be on account of the pre-existing bias in the training dataset due to historical and social factors. In this paper, we focus on a real-world application of credit scoring and construct a fair prediction model by introducing latent variables to remove the correlation between protected attributes, such as sex and age, with the observable feature inputs, including house and job. For detailed implementation, we apply Bayesian approaches, including the Markov Chain Monte Carlo simulation, to estimate our proposed fair model.