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

arXiv: https://arxiv.org/abs/1710.06921 · HTML: https://mlsanity.com/paper/1710.06921/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Oct 2017.

## Built on by (most cited first, 24 of 24)

- [Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey](https://mlsanity.com/paper/2207.07068/) (2022)
- [Fair Preprocessing: Towards Understanding Compositional Fairness of Data Transformers in Machine Learning Pipeline](https://mlsanity.com/paper/2106.06054/) (2021)
- [Exploring How Machine Learning Practitioners (Try To) Use Fairness Toolkits](https://mlsanity.com/paper/2205.06922/) (2022)
- [A Comprehensive Survey of Artificial Intelligence Techniques for Talent Analytics](https://mlsanity.com/paper/2307.03195/) (2023)
- [A Sandbox Tool to Bias(Stress)-Test Fairness Algorithms](https://mlsanity.com/paper/2204.10233/) (2022)
- [OxonFair: A Flexible Toolkit for Algorithmic Fairness](https://mlsanity.com/paper/2407.13710/) (2024)
- [An Empirical Study of Modular Bias Mitigators and Ensembles](https://mlsanity.com/paper/2202.00751/) (2022)
- [A Machine Learning Model for Predicting, Diagnosing, and Mitigating Health Disparities in Hospital Readmission](https://mlsanity.com/paper/2206.06279/) (2022)
- [Trustworthy and Responsible AI for Human-Centric Autonomous Decision-Making Systems](https://mlsanity.com/paper/2408.15550/) (2024)
- [A Review of Fairness and A Practical Guide to Selecting Context-Appropriate Fairness Metrics in Machine Learning](https://mlsanity.com/paper/2411.06624/) (2024)
- [MLHOps: Machine Learning for Healthcare Operations](https://mlsanity.com/paper/2305.02474/) (2023)
- [Explainable AI for clinical risk prediction: a survey of concepts, methods, and modalities](https://mlsanity.com/paper/2308.08407/) (2023)
- [Trustworthy artificial intelligence in the energy sector: Landscape analysis and evaluation framework](https://mlsanity.com/paper/2412.07782/) (2024)
- [Proposing an Interactive Audit Pipeline for Visual Privacy Research](https://mlsanity.com/paper/2111.03984/) (2021)
- [The Right Tool for the Job: Open-Source Auditing Tools in Machine Learning](https://mlsanity.com/paper/2206.10613/) (2022)
- [Navigating Ensemble Configurations for Algorithmic Fairness](https://mlsanity.com/paper/2210.05594/) (2022)
- [A Seven-Layer Model for Standardising AI Fairness Assessment](https://mlsanity.com/paper/2212.11207/) (2022)
- [Addressing Biases in the Texts using an End-to-End Pipeline Approach](https://mlsanity.com/paper/2303.07024/) (2023)
- [Trustworthy, responsible, ethical AI in manufacturing and supply chains: synthesis and emerging research questions](https://mlsanity.com/paper/2305.11581/) (2023)
- [Visual Identification of Problematic Bias in Large Label Spaces](https://mlsanity.com/paper/2201.06386/) (2022)
- [An Approach to Ensure Fairness in News Articles](https://mlsanity.com/paper/2207.03938/) (2022)
- [A Learning and Control Perspective for Microfinance](https://mlsanity.com/paper/2207.12631/) (2022)
- [Being Accountable is Smart: Navigating the Technical and Regulatory Landscape of AI-based Services for Power Grid](https://mlsanity.com/paper/2408.01121/) (2024)
- [humancompatible.detect: a Python Toolkit for Detecting Bias in AI Models](https://mlsanity.com/paper/2509.24340/) (2025)

## Abstract (arXiv)

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.