LocalGLMnet: interpretable deep learning for tabular data

Deep learning models celebrate great success in statistical modeling because they often provide superior predictive power over classical regression models. This success is based on the fact that deep learning models perform representation learning of features, which means that they bring features into the right structure to be able to extract maximal information for the prediction task at hand. This feature engineering is done internally in a nontransparent way by the deep learning model. For this reason deep learning solutions are often criticized to be non-explainable and interpretable, in particular, because this process of representation learning is performed in high-dimensional spaces analyzing bits and pieces of the feature information. Recent research has been focusing on interpreting machine learning predictions in retrospect, see, e.g., Friedman's partial dependence plot (PDP) [10], the accumulated local effects (ALE) method of Apley-Zhu [4], the locally interpretable model-agnostic explanation (LIME) introduced by Ribeiro et al. [23], the SHapley Additive exPlanations (SHAP) of Lundberg-Lee [18] or the marginal attribution by conditioning on quantiles (MACQ) method proposed by Merz et al. [20].