GroupSegment-SHAP: Shapley Value Explanations with Group-Segment Players for Multivariate Time Series

TL;DR

GS-SHAP introduces a novel explanation method for multivariate time series that captures cross-variable and temporal interactions, improving interpretability and efficiency over existing SHAP variants across multiple real-world applications.

Contribution

It proposes GroupSegment SHAP (GS-SHAP), a new approach that constructs explanatory units based on variable dependence and temporal shifts, enhancing interpretability and computational efficiency.

Findings

GS-SHAP improves faithfulness (DeltaAUC) by 1.7x on average.

Reduces runtime by about 40% compared to baseline methods.

Identifies interpretable multivariate interactions in financial markets.

Abstract

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.