timeXplain -- A Framework for Explaining the Predictions of Time Series Classifiers
This work addresses the need for explainable AI in time series analysis, providing a framework for users to understand classifier decisions, though it appears incremental as it builds on existing explainers.
The paper tackles the problem of interpreting predictions from time series classifiers by introducing the timeXplain framework, which extends model-agnostic explainers like SHAP to time series through novel domain mappings and achieves experimental comparison with state-of-the-art methods.
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 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.