dorsal/arxiv
View SchemaGroupSegment-SHAP: Shapley Value Explanations with Group-Segment Players for Multivariate Time Series
| Authors | Jinwoong Kim, Sangjin Park |
|---|---|
| Categories | |
| ArXiv ID | 2601.06114vv1 |
| URL | https://arxiv.org/abs/2601.06114 |
| License | http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
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.
{
"annotation_id": "dff645c0-1ce9-4397-a237-141cc524a06d",
"date_created": "2026-02-17T05:53:05.112000Z",
"date_modified": "2026-02-17T05:53:05.112000Z",
"file_hash": "8bd85c8bedc77e4ed0c8e20eef9d70002fc044c7af49974d9bd9cdc2aceefe83",
"private": false,
"record": {
"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\u0027s 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.",
"arxiv_id": "2601.06114",
"authors": [
"Jinwoong Kim",
"Sangjin Park"
],
"categories": [
"cs.LG",
"cs.AI",
"cs.GT"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"title": "GroupSegment-SHAP: Shapley Value Explanations with Group-Segment Players for Multivariate Time Series",
"url": "https://arxiv.org/abs/2601.06114",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "b1de2418-3671-4a44-bde0-787a1dc7cde8",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}