Z-Time: efficient and effective interpretable multivariate time series classification

Multivariate time series classification has become popular due to its prevalence in many real-world applications. However, most state-of-the-art focuses on improving classification performance, with the best-performing models typically opaque. Interpretable multivariate time series classifiers have been recently introduced, but none can maintain sufficient levels of efficiency and effectiveness together with interpretability. We introduce Z-Time, a novel algorithm for effective and efficient interpretable multivariate time series classification. Z-Time employs temporal abstraction and temporal relations of event intervals to create interpretable features across multiple time series dimensions. In our experimental evaluation on the UEA multivariate time series datasets, Z-Time achieves comparable effectiveness to state-of-the-art non-interpretable multivariate classifiers while being faster than all interpretable multivariate classifiers. We also demonstrate that Z-Time is more robust to missing values and inter-dimensional orders, compared to its interpretable competitors.

Automated summary

Multivariate time series classification is popular in many real-world applications, but most state-of-the-art models focus on improving classification performance without interpretability. We introduce Z-Time, an algorithm that achieves effective and efficient interpretable multivariate time series classification. Z-Time generates interpretable features by utilizing temporal abstraction and temporal relations of event intervals across multiple dimensions. Experimental evaluation shows that Z-Time is comparable in effectiveness to non-interpretable classifiers, while outperforming all interpretable competitors in terms of efficiency.