Actionable Recourse Guided by User Preference

Jayanth Yetukuri, Ian Hardy, Yang Liu

Keywords: Actionable recourse

TL;DR: Capturing user preference and suggesting actionable recourse for adversely affected individuals by a machine learning model.

Abstract: The growing popularity of machine learning models has led to their increased application in domains directly impacting human lives. In critical fields such as healthcare, banking, and criminal justice, tools that ensure trust and transparency are vital for the responsible adoption of these models. One such tool is \emph{actionable recourse} (AR) for negatively impacted users. AR describes recommendations of cost-efficient changes to a user's \emph{actionable} features to help them obtain favorable outcomes. Existing approaches for providing recourse optimize for properties such as proximity, sparsity, validity, and distance-based costs. However, an often-overlooked but crucial requirement for actionability is a consideration of \emph{User Preference} to guide the recourse generation process. Moreover, existing works considering a user's preferences require users to precisely specify their costs for taking actions. This requirement raises questions about the practicality of the corresponding solutions due to the high cognitive loads imposed. In this work, we attempt to capture user preferences via soft constraints in three simple forms: \textit{i) scoring continuous features, ii) bounding feature values} and \textit{iii) ranking categorical features}. We propose an optimization framework that is sensitive to {user preference} and a gradient-based approach to identify \emph{User Preferred Actionable Recourse (UP-AR)}. We empirically demonstrate the proposed approach's superiority in adhering to user preference while maintaining competitive performance in traditional metrics with extensive experiments.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Social Aspects of Machine Learning (eg, AI safety, fairness, privacy, interpretability, human-AI interaction, ethics)