# fairadapt: Causal Reasoning for Fair Data Pre-processing

arXiv: https://arxiv.org/abs/2110.10200 · HTML: https://mlsanity.com/paper/2110.10200/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 55 references that are in the map.
- First posted on arXiv 19 Oct 2021.

## Builds on (most cited first, 9 of 9)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias](https://mlsanity.com/paper/1810.01943/) (2018)
- [Avoiding Discrimination through Causal Reasoning](https://mlsanity.com/paper/1706.02744/) (2017)
- [ranger: A Fast Implementation of Random Forests for High Dimensional Data in C++ and R](https://mlsanity.com/paper/1508.04409/) (2015)
- [The Measure and Mismeasure of Fairness](https://mlsanity.com/paper/1808.00023/) (2018)
- [Fair Data Adaptation with Quantile Preservation](https://mlsanity.com/paper/1911.06685/) (2019)
- [fairmodels: A Flexible Tool For Bias Detection, Visualization, And Mitigation](https://mlsanity.com/paper/2104.00507/) (2021)

## Built on by (most cited first, 16 of 16)

- [Conformalized Fairness via Quantile Regression](https://mlsanity.com/paper/2210.02015/) (2022)
- [Equal Opportunity of Coverage in Fair Regression](https://mlsanity.com/paper/2311.02243/) (2023)
- [Reconciling Predictive and Statistical Parity: A Causal Approach](https://mlsanity.com/paper/2306.05059/) (2023)
- [What Is Fairness? On the Role of Protected Attributes and Fictitious Worlds](https://mlsanity.com/paper/2205.09622/) (2022)
- [Sequential Conditional Transport on Probabilistic Graphs for Interpretable Counterfactual Fairness](https://mlsanity.com/paper/2408.03425/) (2024)
- [FairCauseSyn: Towards Causally Fair LLM-Augmented Synthetic Data Generation](https://mlsanity.com/paper/2506.19082/) (2025)
- [On Optimal Steering to Achieve Exact Fairness](https://mlsanity.com/paper/2509.15759/) (2025)
- [Federated Learning of Quantile Inference under Local Differential Privacy](https://mlsanity.com/paper/2509.21800/) (2025)
- [Towards ethical multimodal systems](https://mlsanity.com/paper/2304.13765/) (2023)
- [Causal Fairness-Guided Dataset Reweighting using Neural Networks](https://mlsanity.com/paper/2311.10512/) (2023)
- [Fair Clustering: A Causal Perspective](https://mlsanity.com/paper/2312.09061/) (2023)
- [Investigating Bias and Fairness in Appearance-based Gaze Estimation](https://mlsanity.com/paper/2604.10707/) (2026)
- [Optimal Transport on Categorical Data for Counterfactuals using Compositional Data and Dirichlet Transport](https://mlsanity.com/paper/2501.15549/) (2025)
- [EquiPy: Sequential Fairness using Optimal Transport in Python](https://mlsanity.com/paper/2503.09866/) (2025)
- [Fair Classification by Direct Intervention on Operating Characteristics](https://mlsanity.com/paper/2509.25481/) (2025)
- [flowengineR: A Modular and Extensible Framework for Fair and Reproducible Workflow Design in R](https://mlsanity.com/paper/2511.00079/) (2025)

## Abstract (arXiv)

Machine learning algorithms are useful for various predictions tasks, but they can also learn how to discriminate, based on gender, race or other sensitive attributes. This realization gave rise to the field of fair machine learning, which aims to measure and mitigate such algorithmic bias. This manuscript describes the R-package fairadapt, which implements a causal inference pre-processing method. By making use of a causal graphical model and the observed data, the method can be used to address hypothetical questions of the form "What would my salary have been, had I been of a different gender/race?". Such individual level counterfactual reasoning can help eliminate discrimination and help justify fair decisions. We also discuss appropriate relaxations which assume certain causal pathways from the sensitive attribute to the outcome are not discriminatory.