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

arXiv: https://arxiv.org/abs/2007.07606 · HTML: https://mlsanity.com/paper/2007.07606/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jul 2020.

## Built on by (most cited first, 9 of 9)

- [Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency](https://mlsanity.com/paper/2306.02109/) (2023)
- [TS-MULE: Local Interpretable Model-Agnostic Explanations for Time Series Forecast Models](https://mlsanity.com/paper/2109.08438/) (2021)
- [Time Series Model Attribution Visualizations as Explanations](https://mlsanity.com/paper/2109.12935/) (2021)
- [Class-Specific Explainability for Deep Time Series Classifiers](https://mlsanity.com/paper/2210.05411/) (2022)
- [Evaluating Explanation Methods for Multivariate Time Series Classification](https://mlsanity.com/paper/2308.15223/) (2023)
- [Towards an MLOps Architecture for XAI in Industrial Applications](https://mlsanity.com/paper/2309.12756/) (2023)
- [Towards transparent and data-driven fault detection in manufacturing: A case study on univariate, discrete time series](https://mlsanity.com/paper/2507.00102/) (2025)
- [Moon: A Modality Conversion-based Efficient Multivariate Time Series Anomaly Detection](https://mlsanity.com/paper/2510.01970/) (2025)
- [Why Did This Model Forecast This Future? Closed-Form Temporal Saliency Towards Causal Explanations of Probabilistic Forecasts](https://mlsanity.com/paper/2206.00679/) (2022)

## Abstract (arXiv)

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.