Legal requirements on explainability in machine learning

Deep learning and other black-box models are becoming more and more popular today. Despite their high performance, they may not be accepted ethically or legally because of their lack of explainability. This paper presents the increasing number of legal requirements on machine learning model interpretability and explainability in the context of private and public decision making. It then explains how those legal requirements can be implemented into machine-learning models and concludes with a call for more inter-disciplinary research on explainability.

Automated summary

Deep learning and other black-box models are increasingly popular, but their lack of explainability may pose ethical and legal challenges. This paper discusses the growing legal requirements for interpretability in machine learning models in decision making contexts and calls for interdisciplinary research to enhance explainability.