Themis-ml: A Fairness-aware Machine Learning Interface for End-to-end Discrimination Discovery and Mitigation

TL;DR

Themis-ml is a comprehensive interface designed to help data scientists and engineers discover and mitigate biases in machine learning models used in socially sensitive applications, promoting fairer decision-making.

Contribution

It introduces a new fairness-aware machine learning interface that supports end-to-end discrimination discovery and mitigation for socially sensitive data.

Findings

Effective in identifying biases in models

Facilitates bias mitigation strategies

Supports end-to-end fairness analysis

Abstract

As more industries integrate machine learning into socially sensitive decision processes like hiring, loan-approval, and parole-granting, we are at risk of perpetuating historical and contemporary socioeconomic disparities. This is a critical problem because on the one hand, organizations who use but do not understand the discriminatory potential of such systems will facilitate the widening of social disparities under the assumption that algorithms are categorically objective. On the other hand, the responsible use of machine learning can help us measure, understand, and mitigate the implicit historical biases in socially sensitive data by expressing implicit decision-making mental models in terms of explicit statistical models. In this paper we specify, implement, and evaluate a "fairness-aware" machine learning interface called themis-ml, which is intended for use by individual data scientists and engineers, academic research teams, or larger product teams who use machine learning in production systems.