Causal Algorithmic Recourse: Foundations and Methods
For practitioners and researchers in trustworthy AI, this work provides a more realistic causal model of algorithmic recourse that accounts for temporal dynamics and latent variability, addressing limitations of existing counterfactual approaches.
The paper develops a causal framework for algorithmic recourse that models repeated decisions on the same individual under varying latent conditions, introducing post-recourse stability conditions and copula-based methods to infer recourse effects from observational data. Experiments on real and semi-synthetic datasets demonstrate the framework's effectiveness.
The trustworthiness of AI decision-making systems is increasingly important. A key feature of such systems is the ability to provide recommendations for how an individual may reverse a negative decision, a problem known as algorithmic recourse. Existing approaches treat recourse outcomes as counterfactuals of a fixed unit, ignoring that real-world recourse involves repeated decisions on the same individual under possibly different latent conditions. We develop a causal framework that models recourse as a process over pre- and post-intervention outcomes, allowing for partial stability and resampling of latent variables. We introduce post-recourse stability conditions that enable reasoning about recourse from observational data alone, and develop a copula-based algorithm for inferring the effects of recourse under these conditions. For settings where paired observations of the same individual before and after intervention are available (called recourse data), we develop methods for inferring copula parameters and performing goodness-of-fit testing. When the copula model is rejected, we provide a distribution-free algorithm for learning recourse effects directly from recourse data. We demonstrate the value of the proposed methods on real and semi-synthetic datasets.