Interpretable and explainable machine learning: A methods‐centric overview with concrete examples

Interpretability and explainability are crucial for machine learning (ML) and statistical applications in medicine, economics, law, and natural sciences and form an essential principle for ML model design and development. Although interpretability and explainability have escaped a precise and universal definition, many models and techniques motivated by these properties have been developed over the last 30 years, with the focus currently shifting toward deep learning. We will consider concrete examples of state‐of‐the‐art, including specially tailored rule‐based, sparse, and additive classification models, interpretable representation learning, and methods for explaining black‐box models post hoc. The discussion will emphasize the need for and relevance of interpretability and explainability, the divide between them, and the inductive biases behind the presented “zoo” of interpretable models and explanation methods. This article is categorized under: Fundamental Concepts of Data and Knowledge > Explainable AI Technologies > Machine Learning Commercial, Legal, and Ethical Issues > Social Considerations Interpretability and explainability are essential principles of machine learning model and method design and development for medicine, economics, law, and natural sciences applications. Over the last 30 years, many techniques motivated by these properties have been developed. This review is intended for a general machine learning audience interested in exploring the challenges of interpretation and explanation beyond the logistic regression or random forest variable importance. We will examine inductive biases behind interpretable and explainable machine learning and illustrate them with concrete examples from the literature.