Improvement-Focused Causal Recourse (ICR)
arXiv:2210.15709 · doi:10.1609/aaai.v37i10.26398
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.
under review
References in corpus (8)
- Fairness in Machine Learning
- The Hidden Assumptions Behind Counterfactual Explanations and Principal Reasons
- Survey on Causal-based Machine Learning Fairness Notions
- Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models
- Strategic Classification is Causal Modeling in Disguise
- On Counterfactual Explanations under Predictive Multiplicity
- Detecting low-complexity unobserved causes
- Linear Classifiers that Encourage Constructive Adaptation