Using Shapley Values and Variational Autoencoders to Explain Predictive Models with Dependent Mixed Features

Shapley values are today extensively used as a model-agnostic explanation framework to explain complex predictive machine learning models. Shapley values have desirable theoretical properties and a sound mathematical foundation. Precise Shapley value estimates for dependent data rely on accurate modeling of the dependencies between all feature combinations. In this paper, we use a variational autoencoder with arbitrary conditioning (VAEAC) to model all feature dependencies simultaneously. We demonstrate through comprehensive simulation studies that VAEAC outperforms the state-of-the-art methods for a wide range of settings for both continuous and mixed dependent features. Finally, we apply VAEAC to the Abalone data set from the UCI Machine Learning Repository.