# On the Fairness of Causal Algorithmic Recourse

arXiv: https://arxiv.org/abs/2010.06529 · HTML: https://mlsanity.com/paper/2010.06529/

## Key facts

- Cited by 70 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Oct 2020.

## Built on by (most cited first, 30 of 70)

- [Towards Causal Representation Learning](https://mlsanity.com/paper/2102.11107/) (2021)
- [Counterfactual Explanations Can Be Manipulated](https://mlsanity.com/paper/2106.02666/) (2021)
- [On the Adversarial Robustness of Causal Algorithmic Recourse](https://mlsanity.com/paper/2112.11313/) (2021)
- [Evaluating Robustness of Counterfactual Explanations](https://mlsanity.com/paper/2103.02354/) (2021)
- [From Statistical to Causal Learning](https://mlsanity.com/paper/2204.00607/) (2022)
- [On the Privacy Risks of Algorithmic Recourse](https://mlsanity.com/paper/2211.05427/) (2022)
- [Robust Counterfactual Explanations in Machine Learning: A Survey](https://mlsanity.com/paper/2402.01928/) (2024)
- [Transport-based Counterfactual Models](https://mlsanity.com/paper/2108.13025/) (2021)
- [Counterfactual Shapley Additive Explanations](https://mlsanity.com/paper/2110.14270/) (2021)
- [Prompting Fairness: Integrating Causality to Debias Large Language Models](https://mlsanity.com/paper/2403.08743/) (2024)
- [What-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspective](https://mlsanity.com/paper/2206.04101/) (2022)
- [CounterNet: End-to-End Training of Prediction Aware Counterfactual Explanations](https://mlsanity.com/paper/2109.07557/) (2021)
- [Backtracking Counterfactuals](https://mlsanity.com/paper/2211.00472/) (2022)
- [Counterfactual Fairness Is Basically Demographic Parity](https://mlsanity.com/paper/2208.03843/) (2022)
- [Equal Improvability: A New Fairness Notion Considering the Long-term Impact](https://mlsanity.com/paper/2210.06732/) (2022)
- [Setting the Right Expectations: Algorithmic Recourse Over Time](https://mlsanity.com/paper/2309.06969/) (2023)
- [Modulating Language Model Experiences through Frictions](https://mlsanity.com/paper/2407.12804/) (2024)
- [Robustness Implies Fairness in Causal Algorithmic Recourse](https://mlsanity.com/paper/2302.03465/) (2023)
- [Low-Cost Algorithmic Recourse for Users With Uncertain Cost Functions](https://mlsanity.com/paper/2111.01235/) (2021)
- [Personalized Algorithmic Recourse with Preference Elicitation](https://mlsanity.com/paper/2205.13743/) (2022)
- ["Explain it in the Same Way!" -- Model-Agnostic Group Fairness of Counterfactual Explanations](https://mlsanity.com/paper/2211.14858/) (2022)
- [Fairness Aware Counterfactuals for Subgroups](https://mlsanity.com/paper/2306.14978/) (2023)
- [Designing Long-term Group Fair Policies in Dynamical Systems](https://mlsanity.com/paper/2311.12447/) (2023)
- [Fairness in Algorithmic Recourse Through the Lens of Substantive Equality of Opportunity](https://mlsanity.com/paper/2401.16088/) (2024)
- [Addressing Strategic Manipulation Disparities in Fair Classification](https://mlsanity.com/paper/2205.10842/) (2022)
- [The Utility of "Even if..." Semifactual Explanation to Optimise Positive Outcomes](https://mlsanity.com/paper/2310.18937/) (2023)
- [Time Can Invalidate Algorithmic Recourse](https://mlsanity.com/paper/2410.08007/) (2024)
- [Feature Responsiveness Scores: Model-Agnostic Explanations for Recourse](https://mlsanity.com/paper/2410.22598/) (2024)
- [Incentivizing Desirable Effort Profiles in Strategic Classification: The Role of Causality and Uncertainty](https://mlsanity.com/paper/2502.06749/) (2025)
- [Causal Learning for Socially Responsible AI](https://mlsanity.com/paper/2104.12278/) (2021)

## Abstract (arXiv)

Algorithmic fairness is typically studied from the perspective of predictions. Instead, here we investigate fairness from the perspective of recourse actions suggested to individuals to remedy an unfavourable classification. We propose two new fairness criteria at the group and individual level, which -- unlike prior work on equalising the average group-wise distance from the decision boundary -- explicitly account for causal relationships between features, thereby capturing downstream effects of recourse actions performed in the physical world. We explore how our criteria relate to others, such as counterfactual fairness, and show that fairness of recourse is complementary to fairness of prediction. We study theoretically and empirically how to enforce fair causal recourse by altering the classifier and perform a case study on the Adult dataset. Finally, we discuss whether fairness violations in the data generating process revealed by our criteria may be better addressed by societal interventions as opposed to constraints on the classifier.