Improvement-Focused Causal Recourse (ICR)

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.

arXiv commentunder review

References in corpus (17)

• Counterfactual Fairness
• Actionable Recourse in Linear Classification
• Fairness in Machine Learning
• The Hidden Assumptions Behind Counterfactual Explanations and Principal Reasons
• Algorithmic recourse under imperfect causal knowledge: a probabilistic approach
• Algorithmic Recourse: from Counterfactual Explanations to Interventions
• Survey on Causal-based Machine Learning Fairness Notions
• Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability
• Predictive Multiplicity in Classification
• Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models
• Shapley Flow: A Graph-based Approach to Interpreting Model Predictions
• Strategic Classification is Causal Modeling in Disguise
• On Counterfactual Explanations under Predictive Multiplicity
• Decisions, Counterfactual Explanations and Strategic Behavior
• Detecting low-complexity unobserved causes
• The Intriguing Relation Between Counterfactual Explanations and Adversarial Examples
• Linear Classifiers that Encourage Constructive Adaptation

Cited by in corpus (1)

• Scientific Inference With Interpretable Machine Learning: Analyzing Models to Learn About Real-World Phenomena