timeXplain – A Framework for Explaining the Predictions of Time Series Classifiers [article]

Felix Mujkanovic, Vanja Doskoč, Martin Schirneck, Patrick Schäfer, Tobias Friedrich
2023 arXiv   pre-print
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
more » ... on and value prediction. We present novel domain mappings for the time domain, frequency domain, and time series statistics and analyze their explicative power as well as their limits. We employ a novel evaluation metric to experimentally compare timeXplain to several model-specific explanation approaches for state-of-the-art time series classifiers.
arXiv:2007.07606v2 fatcat:z2j3ghnoh5g5tbqzfb2odobfpe