# Causal Fairness for Outcome Control

arXiv: https://arxiv.org/abs/2306.05066 · HTML: https://mlsanity.com/paper/2306.05066/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 47 references that are in the map.
- First posted on arXiv 8 Jun 2023.

## Builds on (most cited first, 16 of 16)

- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Avoiding Discrimination through Causal Reasoning](https://mlsanity.com/paper/1706.02744/) (2017)
- [Path-Specific Counterfactual Fairness](https://mlsanity.com/paper/1802.08139/) (2018)
- [Fair Inference On Outcomes](https://mlsanity.com/paper/1705.10378/) (2017)
- [Discrimination in Online Ad Delivery](https://mlsanity.com/paper/1301.6822/) (2013)
- [Automated Experiments on Ad Privacy Settings: A Tale of Opacity, Choice, and Discrimination](https://mlsanity.com/paper/1408.6491/) (2014)
- [Counterfactual Probabilities: Computational Methods, Bounds and Applications](https://mlsanity.com/paper/1302.6784/) (2013)
- [PC-Fairness: A Unified Framework for Measuring Causality-based Fairness](https://mlsanity.com/paper/1910.12586/) (2019)
- [Counterfactual Risk Assessments, Evaluation, and Fairness](https://mlsanity.com/paper/1909.00066/) (2019)
- [Balanced Policy Evaluation and Learning](https://mlsanity.com/paper/1705.07384/) (2017)
- [Causal Fairness Analysis](https://mlsanity.com/paper/2207.11385/) (2022)
- [Fairness Through Causal Awareness: Learning Latent-Variable Models for Biased Data](https://mlsanity.com/paper/1809.02519/) (2018)
- [Causal Conceptions of Fairness and their Consequences](https://mlsanity.com/paper/2207.05302/) (2022)
- [Fair Data Adaptation with Quantile Preservation](https://mlsanity.com/paper/1911.06685/) (2019)
- [Counterfactual harm](https://mlsanity.com/paper/2204.12993/) (2022)
- [Principal Fairness for Human and Algorithmic Decision-Making](https://mlsanity.com/paper/2005.10400/) (2020)

## Built on by (most cited first, 8 of 8)

- [Fairness-Accuracy Trade-Offs: A Causal Perspective](https://mlsanity.com/paper/2405.15443/) (2024)
- [Local Causal Discovery for Structural Evidence of Direct Discrimination](https://mlsanity.com/paper/2405.14848/) (2024)
- [Group-blind optimal transport to group parity and its constrained variants](https://mlsanity.com/paper/2310.11407/) (2023)
- [What Hides behind Unfairness? Exploring Dynamics Fairness in Reinforcement Learning](https://mlsanity.com/paper/2404.10942/) (2024)
- [A Causal Lens for Learning Long-term Fair Policies](https://mlsanity.com/paper/2506.11242/) (2025)
- [Mind the Gap: A Causal Perspective on Bias Amplification in Prediction & Decision-Making](https://mlsanity.com/paper/2405.15446/) (2024)
- [A pipeline for enabling path-specific causal fairness in observational health data](https://mlsanity.com/paper/2601.09841/) (2026)
- [Minimax Optimal Regret for Causal Logistic Bandits with Counterfactual Fairness](https://mlsanity.com/paper/2610.01377/) (2026)

## Abstract (arXiv)

As society transitions towards an AI-based decision-making infrastructure, an ever-increasing number of decisions once under control of humans are now delegated to automated systems. Even though such developments make various parts of society more efficient, a large body of evidence suggests that a great deal of care needs to be taken to make such automated decision-making systems fair and equitable, namely, taking into account sensitive attributes such as gender, race, and religion. In this paper, we study a specific decision-making task called outcome control in which an automated system aims to optimize an outcome variable Y while being fair and equitable. The interest in such a setting ranges from interventions related to criminal justice and welfare, all the way to clinical decision-making and public health. In this paper, we first analyze through causal lenses the notion of benefit, which captures how much a specific individual would benefit from a positive decision, counterfactually speaking, when contrasted with an alternative, negative one. We introduce the notion of benefit fairness, which can be seen as the minimal fairness requirement in decision-making, and develop an algorithm for satisfying it. We then note that the benefit itself may be influenced by the protected attribute, and propose causal tools which can be used to analyze this. Finally, if some of the variations of the protected attribute in the benefit are considered as discriminatory, the notion of benefit fairness may need to be strengthened, which leads us to articulating a notion of causal benefit fairness. Using this notion, we develop a new optimization procedure capable of maximizing Y while ascertaining causal fairness in the decision process.