Improvement-Focused Causal Recourse (ICR)
It addresses a critical flaw in recourse recommendations for stakeholders affected by algorithmic decisions, though it appears incremental as it builds on prior causal recourse work.
The paper tackles the problem that existing algorithmic recourse methods may recommend actions that fool the predictor without improving the underlying real-world state, and introduces Improvement-Focused Causal Recourse (ICR) to guarantee both acceptance and improvement when causal knowledge is correct.
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.