Algorithmic Recourse: from Counterfactual Explanations to Interventions

Abstract

As machine learning is increasingly used to inform consequential decision-making (e.g., pre-trial bail and loan approval), it becomes important to explain how the system arrived at its decision, and also suggest actions to achieve a favorable decision. Counterfactual explanations -- "how the world would have (had) to be different for a desirable outcome to occur" -- aim to satisfy these criteria. Existing works have primarily focused on designing algorithms to obtain counterfactual explanations for a wide range of settings. However, one of the main objectives of "explanations as a means to help a data-subject act rather than merely understand" has been overlooked. In layman's terms, counterfactual explanations inform an individual where they need to get to, but not how to get there. In this work, we rely on causal reasoning to caution against the use of counterfactual explanations as a recommendable set of actions for recourse. Instead, we propose a shift of paradigm from recourse via nearest counterfactual explanations to recourse through minimal interventions, moving the focus from explanations to recommendations. Finally, we provide the reader with an extensive discussion on how to realistically achieve recourse beyond structural interventions.

References in corpus (15)

• Towards A Rigorous Science of Interpretable Machine Learning
• Interpretable machine learning: definitions, methods, and applications
• Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations
• Counterfactual Fairness
• Actionable Recourse in Linear Classification
• The Hidden Assumptions Behind Counterfactual Explanations and Principal Reasons
• Local Rule-Based Explanations of Black Box Decision Systems
• An Evaluation of the Human-Interpretability of Explanation
• Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems
• Model-Agnostic Counterfactual Explanations for Consequential Decisions
• Interventions over Predictions: Reframing the Ethical Debate for Actuarial Risk Assessment
• Inverse Classification for Comparison-based Interpretability in Machine Learning
• Causal Consistency of Structural Equation Models
• Equalizing Recourse across Groups
• Synthesizing Action Sequences for Modifying Model Decisions

Cited by in corpus (27)

• Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers
• Algorithmic recourse under imperfect causal knowledge: a probabilistic approach
• Explainable Machine Learning for Public Policy: Use Cases, Gaps, and Research Directions
• Counterfactual Shapley Additive Explanations
• On Tackling Explanation Redundancy in Decision Trees
• A survey of algorithmic recourse: definitions, formulations, solutions, and prospects
• Towards Robust and Reliable Algorithmic Recourse
• A Framework and Benchmarking Study for Counterfactual Generating Methods on Tabular Data
• Appropriate Fairness Perceptions? On the Effectiveness of Explanations in Enabling People to Assess the Fairness of Automated Decision Systems
• On Counterfactual Explanations under Predictive Multiplicity
• Rational Shapley Values
• Achieving Diversity in Counterfactual Explanations: a Review and Discussion
• Setting the Right Expectations: Algorithmic Recourse Over Time
• Improvement-Focused Causal Recourse (ICR)
• Rationalizing Predictions by Adversarial Information Calibration
• Optimal Counterfactual Explanations in Tree Ensembles
• Endogenous Macrodynamics in Algorithmic Recourse
• Towards the Unification and Robustness of Perturbation and Gradient Based Explanations
• Framing Algorithmic Recourse for Anomaly Detection
• Seven challenges for harmonizing explainability requirements
• Counterfactual Explanations for Machine Learning: Challenges Revisited
• Counterfactual Situation Testing: From Single to Multidimensional Discrimination
• Towards Feasible Counterfactual Explanations: A Taxonomy Guided Template-based NLG Method
• Everything is Relative: Understanding Fairness with Optimal Transport
• Simulating counterfactuals
• Estimation of Counterfactual Interventions under Uncertainties
• SafeAR: Safe Algorithmic Recourse by Risk-Aware Policies