Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems
This addresses the need for realistic recourse in fairness literature, offering an alternative to counterfactual explanations for individuals impacted by ML decisions.
The paper tackles the problem of providing actionable recourse for individuals affected by black-box decision-making systems, such as those denied credit, by proposing an algorithm that models the underlying data distribution to generate the smallest set of changes needed to improve outcomes, applicable to both supervised classification and causal systems.
Machine learning based decision making systems are increasingly affecting humans. An individual can suffer an undesirable outcome under such decision making systems (e.g. denied credit) irrespective of whether the decision is fair or accurate. Individual recourse pertains to the problem of providing an actionable set of changes a person can undertake in order to improve their outcome. We propose a recourse algorithm that models the underlying data distribution or manifold. We then provide a mechanism to generate the smallest set of changes that will improve an individual's outcome. This mechanism can be easily used to provide recourse for any differentiable machine learning based decision making system. Further, the resulting algorithm is shown to be applicable to both supervised classification and causal decision making systems. Our work attempts to fill gaps in existing fairness literature that have primarily focused on discovering and/or algorithmically enforcing fairness constraints on decision making systems. This work also provides an alternative approach to generating counterfactual explanations.