Improvement-Focused Causal Recourse (ICR)

TL;DR

This paper introduces Improvement-Focused Causal Recourse (ICR), a novel method that ensures recommended actions lead to real-world improvement and acceptance by leveraging causal knowledge, unlike previous approaches.

Contribution

ICR shifts the focus to guiding actions that ensure real-world improvement and acceptance without tailoring to specific predictors, using causal knowledge for better decision system design.

Findings

ICR guarantees both acceptance and real-world improvement given correct causal knowledge.

ICR outperforms existing causal recourse methods in guiding towards meaningful change.

The method emphasizes causal understanding over predictor-specific adjustments.

Abstract

Algorithmic recourse recommendations, such as Karimi et al.'s (2021) causal recourse (CR), inform stakeholders of how to act to revert unfavourable decisions. However, some actions lead to acceptance (i.e., revert the model's decision) but do not lead to improvement (i.e., may not revert the underlying real-world state). To recommend such actions is to recommend fooling the predictor. We introduce a novel method, Improvement-Focused Causal Recourse (ICR), which involves a conceptual shift: Firstly, we require ICR recommendations to guide towards improvement. Secondly, we do not tailor the recommendations to be accepted by a specific predictor. Instead, we leverage causal knowledge to design decision systems that predict accurately pre- and post-recourse. As a result, improvement guarantees translate into acceptance guarantees. We demonstrate that given correct causal knowledge, ICR, in contrast to existing approaches, guides towards both acceptance and improvement.