Time Can Invalidate Algorithmic Recourse
arXiv:2410.08007 · doi:10.1145/3715275.3732008
Abstract
Algorithmic Recourse (AR) aims to provide users with actionable steps to overturn unfavourable decisions made by machine learning predictors. However, these actions often take time to implement (e.g., getting a degree can take years), and their effects may vary as the world evolves. Thus, it is natural to ask for recourse that remains valid in a dynamic environment. In this paper, we study the robustness of algorithmic recourse over time by casting the problem through the lens of causality. We demonstrate theoretically and empirically that (even robust) causal AR methods can fail over time, except in the -- unlikely -- case that the world is stationary. Even more critically, unless the world is fully deterministic, counterfactual AR cannot be solved optimally. To account for this, we propose a simple yet effective algorithm for temporal AR that explicitly accounts for time under the assumption of having access to an estimator approximating the stochastic process. Our simulations on synthetic and realistic datasets show how considering time produces more resilient solutions to potential trends in the data distribution.
arXiv commentThis is a preprint of a paper accepted at FAccT 2025. The content is identical to the published version, apart from minor cosmetic changes
References in corpus (10)
- Array Programming with NumPy
- Artificial Intelligence: the global landscape of ethics guidelines
- 'It's Reducing a Human Being to a Percentage'; Perceptions of Justice in Algorithmic Decisions
- Actionable Recourse in Linear Classification
- Counterfactual Explanations for Machine Learning on Multivariate Time Series Data
- BeFair: Addressing Fairness in the Banking Sector
- Synthesizing explainable counterfactual policies for algorithmic recourse with program synthesis
- Setting the Right Expectations: Algorithmic Recourse Over Time
- Exploiting Preference Elicitation in Interactive and User-centered Algorithmic Recourse: An Initial Exploration
- Endogenous Macrodynamics in Algorithmic Recourse