A survey of algorithmic recourse: definitions, formulations, solutions, and prospects

TL;DR

This survey comprehensively reviews the concept of algorithmic recourse, discussing its definitions, formulations, solutions, and future research directions, emphasizing its importance in ethical and fair AI decision-making.

Contribution

It unifies diverse definitions and approaches to algorithmic recourse and outlines future research challenges and connections to ethical issues.

Findings

Unified definitions and formulations of recourse

Overview of existing solution methods

Identification of future research directions

Abstract

Machine learning is increasingly used to inform decision-making in sensitive situations where decisions have consequential effects on individuals' lives. In these settings, in addition to requiring models to be accurate and robust, socially relevant values such as fairness, privacy, accountability, and explainability play an important role for the adoption and impact of said technologies. In this work, we focus on algorithmic recourse, which is concerned with providing explanations and recommendations to individuals who are unfavourably treated by automated decision-making systems. We first perform an extensive literature review, and align the efforts of many authors by presenting unified definitions, formulations, and solutions to recourse. Then, we provide an overview of the prospective research directions towards which the community may engage, challenging existing assumptions and making explicit connections to other ethical challenges such as security, privacy, and fairness.