Performative Validity of Recourse Explanations

TL;DR

This paper examines how the act of providing recourse explanations can influence applicant behavior and data, potentially invalidating the explanations over time due to performativity effects, and emphasizes the importance of causal recourse methods.

Contribution

It formally characterizes the conditions under which recourse explanations remain valid despite performativity effects and highlights the risks of non-causal interventions.

Findings

Recourse actions can become invalid if they target non-causal variables.

Standard counterfactual explanations may be unreliable under performativity.

Causal recourse methods are recommended to ensure validity.

Abstract

When applicants get rejected by an algorithmic decision system, recourse explanations provide actionable suggestions for how to change their input features to get a positive evaluation. A crucial yet overlooked phenomenon is that recourse explanations are performative: When many applicants act according to their recommendations, their collective behavior may change statistical regularities in the data and, once the model is refitted, also the decision boundary. Consequently, the recourse algorithm may render its own recommendations invalid, such that applicants who make the effort of implementing their recommendations may be rejected again when they reapply. In this work, we formally characterize the conditions under which recourse explanations remain valid under performativity. A key finding is that recourse actions may become invalid if they are influenced by or if they intervene on non-causal variables. Based on our analysis, we caution against the use of standard counterfactual explanations and causal recourse methods, and instead advocate for recourse methods that recommend actions exclusively on causal variables.