GroupSegment-SHAP: Shapley Value Explanations with Group-Segment Players for Multivariate Time Series
Not on the map. Why?
Abstract (arXiv)
Multivariate time-series models achieve strong predictive performance in healthcare, industry, energy, and finance, but how they combine cross-variable interactions with temporal dynamics remains unclear. SHapley Additive exPlanations (SHAP) are widely used for interpretation. However, existing time-series variants typically treat the feature and time axes independently, fragmenting structural signals formed jointly by multiple variables over specific intervals. We propose GroupSegment SHAP (GS-SHAP), which constructs explanatory units as group-segment players based on cross-variable dependence and distribution shifts over time, and then quantifies each unit's contribution via Shapley attribution. We evaluate GS-SHAP across four real-world domains: human activity recognition, power-system forecasting, medical signal analysis, and financial time series, and compare it with KernelSHAP, TimeSHAP, SequenceSHAP, WindowSHAP, and TSHAP. GS-SHAP improves deletion-based faithfulness (DeltaAUC) by about 1.7x on average over time-series SHAP baselines, while reducing wall-clock runtime by about 40 percent on average under matched perturbation budgets. A financial case study shows that GS-SHAP identifies interpretable multivariate-temporal interactions among key market variables during high-volatility regimes.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 24 of its 72 references that are in the map. First posted on arXiv 3 Jan 2026.
Builds on
24 of 72 references.
References · 24
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
- 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
- 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
- 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,416
- 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,013
- 2020Time Series Forecasting With Deep Learning: A Surveycited by 459
- 2018On the Robustness of Interpretability Methodscited by 314
- 2017Multitask learning and benchmarking with clinical time series datacited by 290
- 2019Explaining individual predictions when features are dependent: More accurate approximations to Shapley valuescited by 208
- 2020Problems with Shapley-value-based explanations as feature importance measurescited by 200
- 2019The Shapley Taylor Interaction Indexcited by 143
12 more
- 2020Benchmarking Deep Learning Interpretability in Time Series Predictionscited by 102
- 2020TimeSHAP: Explaining Recurrent Models through Sequence Perturbationscited by 74
- 2021Explainable Artificial Intelligence (XAI) on TimeSeries Data: A Surveycited by 72
- 2017Toeplitz Inverse Covariance-Based Clustering of Multivariate Time Series Datacited by 47
- 2021Temporal Dependencies in Feature Importance for Time Series Predictionscited by 27
- 2022WindowSHAP: An Efficient Framework for Explaining Time-series Classifiers based on Shapley Valuescited by 24
- 2021groupShapley: Efficient prediction explanation with Shapley values for feature groupscited by 21
- 2024A Survey of Explainable Artificial Intelligence (XAI) in Financial Time Series Forecastingcited by 14
- 2025Deep Learning for Time Series Forecasting: A Surveycited by 10
- 2024Improving the Weighting Strategy in KernelSHAPcited by 5
- 2025C-SHAP for time series: An approach to high-level temporal explanationscited by 3
- 2025IKNet: Interpretable Stock Price Prediction via Keyword-Guided Integration of News and Technical Indicatorscited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.