Algorithmic Recourse: from Counterfactual Explanations to Interventions

TL;DR

This paper shifts the focus from counterfactual explanations to actionable interventions for recourse in machine learning decisions, emphasizing causal reasoning and practical implementation beyond mere explanations.

Contribution

It introduces a paradigm change from using nearest counterfactual explanations to recommending minimal interventions for effective recourse, grounded in causal reasoning.

Findings

Highlights limitations of counterfactual explanations for actionable recourse

Proposes a shift to intervention-based recourse strategies

Discusses practical considerations for implementing 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.