# An Empirical Study of Explainable AI Techniques on Deep Learning Models For Time Series Tasks

arXiv: https://arxiv.org/abs/2012.04344 · HTML: https://mlsanity.com/paper/2012.04344/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Dec 2020.

## Built on by (most cited first, 8 of 8)

- [TS-MULE: Local Interpretable Model-Agnostic Explanations for Time Series Forecast Models](https://mlsanity.com/paper/2109.08438/) (2021)
- [A Deep Dive into Perturbations as Evaluation Technique for Time Series XAI](https://mlsanity.com/paper/2307.05104/) (2023)
- [Time Series Model Attribution Visualizations as Explanations](https://mlsanity.com/paper/2109.12935/) (2021)
- [Prototypes as Explanation for Time Series Anomaly Detection](https://mlsanity.com/paper/2307.01601/) (2023)
- [Introducing the Attribution Stability Indicator: a Measure for Time Series XAI Attributions](https://mlsanity.com/paper/2310.04178/) (2023)
- [Towards Explainable Artificial Intelligence in Banking and Financial Services](https://mlsanity.com/paper/2112.08441/) (2021)
- [Towards Explainable Deep Clustering for Time Series Data](https://mlsanity.com/paper/2507.20840/) (2025)
- [Interpretable deep convolutional model for nonlinear multivariate time series in complex systems](https://mlsanity.com/paper/2501.04339/) (2025)

## Abstract (arXiv)

Decision explanations of machine learning black-box models are often generated by applying Explainable AI (XAI) techniques. However, many proposed XAI methods produce unverified outputs. Evaluation and verification are usually achieved with a visual interpretation by humans on individual images or text. In this preregistration, we propose an empirical study and benchmark framework to apply attribution methods for neural networks developed for images and text data on time series. We present a methodology to automatically evaluate and rank attribution techniques on time series using perturbation methods to identify reliable approaches.