On the Fairness of Causal Algorithmic Recourse
This work addresses fairness for individuals seeking recourse in algorithmic decision-making, offering a novel causal perspective that goes beyond incremental improvements by highlighting potential societal interventions.
The paper tackles the problem of ensuring fairness in algorithmic recourse actions, which suggest changes to individuals to reverse unfavorable classifications, by proposing new group and individual fairness criteria that incorporate causal relationships to capture real-world effects. It demonstrates the complementarity of recourse fairness to prediction fairness and explores enforcement methods through theoretical analysis and a case study on the Adult dataset.
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.