timeXplain -- A Framework for Explaining the Predictions of Time Series Classifiers

Modern time series classifiers display impressive predictive capabilities, yet their decision-making processes mostly remain black boxes to the user. At the same time, model-agnostic explainers, such as the recently proposed SHAP, promise to make the predictions of machine learning models interpretable, provided there are well-designed domain mappings. We bring both worlds together in our timeXplain framework, extending the reach of explainable artificial intelligence to time series classification and value prediction. We present novel domain mappings for the time and the frequency domain as well as series statistics and analyze their explicative power as well as their limits. We employ timeXplain in a large-scale experimental comparison of several state-of-the-art time series classifiers and discover similarities between seemingly distinct classification concepts such as residual neural networks and elastic ensembles.