# An Empirical Evaluation of Factors Affecting SHAP Explanation of Time Series Classification

arXiv: https://arxiv.org/abs/2509.03649 · HTML: https://mlsanity.com/paper/2509.03649/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 28 references that are in the map.
- First posted on arXiv 3 Sep 2025.

## Builds on (most cited first, 14 of 14)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Captum: A unified and generic model interpretability library for PyTorch](https://mlsanity.com/paper/2009.07896/) (2020)
- [MINIROCKET: A Very Fast (Almost) Deterministic Transform for Time Series Classification](https://mlsanity.com/paper/2012.08791/) (2020)
- [sktime: A Unified Interface for Machine Learning with Time Series](https://mlsanity.com/paper/1909.07872/) (2019)
- [Evaluation of post-hoc interpretability methods in time-series classification](https://mlsanity.com/paper/2202.05656/) (2022)
- [aeon: a Python toolkit for learning from time series](https://mlsanity.com/paper/2406.14231/) (2024)
- [ClaSP -- Parameter-free Time Series Segmentation](https://mlsanity.com/paper/2207.13987/) (2022)
- [QUANT: A Minimalist Interval Method for Time Series Classification](https://mlsanity.com/paper/2308.00928/) (2023)
- [dCAM: Dimension-wise Class Activation Map for Explaining Multivariate Data Series Classification](https://mlsanity.com/paper/2207.12165/) (2022)
- [Scalable Classifier-Agnostic Channel Selection for Multivariate Time Series Classification](https://mlsanity.com/paper/2206.09274/) (2022)
- [Greedy Gaussian Segmentation of Multivariate Time Series](https://mlsanity.com/paper/1610.07435/) (2016)
- [Improving the Evaluation and Actionability of Explanation Methods for Multivariate Time Series Classification](https://mlsanity.com/paper/2406.12507/) (2024)

## Built on by (most cited first, 1 of 1)

- [DynSHAP: Towards Explainable Dynamic Survival Analysis](https://mlsanity.com/paper/2609.13042/) (2026)

## Abstract (arXiv)

Explainable AI (XAI) has become an increasingly important topic for understanding and attributing the predictions made by complex Time Series Classification (TSC) models. Among attribution methods, SHapley Additive exPlanations (SHAP) is widely regarded as an excellent attribution method; but its computational complexity, which scales exponentially with the number of features, limits its practicality for long time series. To address this, recent studies have shown that aggregating features via segmentation, to compute a single attribution value for a group of consecutive time points, drastically reduces SHAP running time. However, the choice of the optimal segmentation strategy remains an open question. In this work, we investigated eight different Time Series Segmentation algorithms to understand how segment compositions affect the explanation quality. We evaluate these approaches using two established XAI evaluation methodologies: InterpretTime and AUC Difference. Through experiments on both Multivariate (MTS) and Univariate Time Series (UTS), we find that the number of segments has a greater impact on explanation quality than the specific segmentation method. Notably, equal-length segmentation consistently outperforms most of the custom time series segmentation algorithms. Furthermore, we introduce a novel attribution normalisation technique that weights segments by their length and we show that it consistently improves attribution quality.