Evaluating Simplification Algorithms for Interpretability of Time Series Classification
This work addresses the challenge of making time series data more interpretable for humans, which is incremental as it focuses on evaluation metrics rather than new simplification methods.
The paper tackles the problem of evaluating simplification algorithms for improving interpretability in time series classification by introducing metrics based on complexity and loyalty, and experimentally tests four algorithms across various classifiers and datasets, finding that simplifications with high Shapley value aid interpretability and confirming utility through human evaluation.
In this work, we introduce metrics to evaluate the use of simplified time series in the context of interpretability of a TSC -- a Time Series Classifier. Such simplifications are important because time series data, in contrast to text and image data, are not intuitively under- standable to humans. These metrics are related to the complexity of the simplifications -- how many segments they contain -- and to their loyalty -- how likely they are to maintain the classification of the original time series. We focus on simplifications that select a subset of the original data points, and show that these typically have high Shapley value, thereby aiding interpretability. We employ these metrics to experimentally evaluate four distinct simplification algorithms, across several TSC algorithms and across datasets of varying characteristics, from seasonal or stationary to short or long. We subsequently perform a human-grounded evaluation with forward simulation, that confirms also the practical utility of the introduced metrics to evaluate the use of simplifications in the context of interpretability of TSC. Our findings are summarized in a framework for deciding, for a given TSC, if the various simplifications are likely to aid in its interpretability.