Software: ale: Interpretable Machine Learning and Statistical Inference with Accumulated Local Effects (ALE)
explainable AI, XAI, interpretable machine learning, IML, accumulated local effects, ALE, statistics, statistical inference, bootstrap
Abstract
Accumulated Local Effects (ALE) were initially developed as a model-agnostic approach for global explanations of the results of black-box machine learning algorithms. (Apley, Daniel W., and Jingyu Zhu. "Visualizing the effects of predictor variables in black box supervised learning models." Journal of the Royal Statistical Society Series B: Statistical Methodology 82.4 (2020): 1059-1086 .) ALE has two primary advantages over other approaches like partial dependency plots (PDP) and SHapley Additive exPlanations (SHAP): its values are not affected by the presence of interactions among variables in a model and its computation is relatively rapid. This package rewrites the original code from the 'ALEPlot' package for calculating ALE data and it completely reimplements the plotting of ALE values. Future versions hope to extend the original ALE concept beyond global explanations with ALE-based measures that can be used for statistical inference as well as an ALE-based approach for local explanations.