Two Types of Explainability for Machine Learning Models

This paper argues that there are two different types of causes that we can wish to understand when we talk about wanting machine learning models to be explainable. The first are causes in the features that a model uses to make its predictions. The second are causes in the world that have enabled those features to carry out the model’s predictive function. I argue that this difference should be seen as giving rise to two distinct types of explanation and explainability and show how the proposed distinction proves useful in a number of applications.