Convex optimization for actionable \& plausible counterfactual explanations
This work provides incremental improvements for enhancing transparency in decision-making systems, particularly in domains requiring intuitive explanations.
The authors tackled the problem of generating counterfactual explanations in machine learning by enhancing their previous convex optimization method to ensure actionability and plausibility, addressing limitations in existing approaches that often ignore feature dependencies.
Transparency is an essential requirement of machine learning based decision making systems that are deployed in real world. Often, transparency of a given system is achieved by providing explanations of the behavior and predictions of the given system. Counterfactual explanations are a prominent instance of particular intuitive explanations of decision making systems. While a lot of different methods for computing counterfactual explanations exist, only very few work (apart from work from the causality domain) considers feature dependencies as well as plausibility which might limit the set of possible counterfactual explanations. In this work we enhance our previous work on convex modeling for computing counterfactual explanations by a mechanism for ensuring actionability and plausibility of the resulting counterfactual explanations.