awesome-time-series-explainability
github.com/jhoelli/awesome-time-series-explainability ↗A list of (post-hoc) XAI for time series
183
GitHub Stars
72
Curated Resources
8
Categories
22 hours ago
Last Refreshed
OutlineSurveysLibrariesClassificationForecastingClassification and Regression / ForcastingBenchmarking and EvaluationAnte-Hoc Explanation
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me feature attribution resources from awesome-time-series-explainability"
Installation instructions →What's inside
Benchmarking and Evaluation
- A Deep Dive into Perturbations as Evaluation Technique for Time Series XAI
- A Deep Dive into Perturbations as Evaluation Technique for Time Series XAI
- Evaluating Explanation Methods for Multivariate Time Series Classification
- Evaluation of post-hoc interpretability methods in time-series classification
- Exathlon: A Benchmark for Explainable Anomaly Detection over Time Series
- Introducing the Attribution Stability Indicator: a Measure for Time Series XAI Attributions
Classification
- Agnostic Local Explanation for Time Series ClassificationFeature Attribution
- Attention-Based Counterfactual Explanation for Multivariate Time SeriesCounterfactuals
- Benchmarking Deep Learning Interpretability in Time Series PredictionsFeature Attribution
- CELS: Counterfactual Explanations for Time Series Data via Learned Saliency MapsCounterfactuals
- Class-Specific Explainability for Deep Time Series ClassifiersFeature Attribution
- Counterfactual explanations for multivariate time seriesCounterfactuals
Ante-Hoc Explanation
- A memory-network based solution for multivariate time-series forecastingForecasting
- Explainable Failure Predictions with RNN Classifiers based on Time Series DataClassification
- Explaining Deep Classification of Time-Series Data with Learned PrototypesClassification
- Exploring interpretable LSTM neural networks over multi-variable dataForecasting
- Fast, accurate and explainable time series classification through randomizationClassification
- Interpretable Multivariate Time Series Forecasting with Temporal Attention Convolutional Neural NetworksForecasting
Outline
Surveys
- A Survey of Explainable Artificial Intelligence (XAI) in Financial Time Series Forecasting
- Explainable AI for time series classification: a review, taxonomy and research directions
- Explainable artificial intelligence (XAI) in finance: a systematic literature review
- Explainable artificial intelligence (xai) on timeseries data: A survey
- Post Hoc Explainability for Time Series Classification: Toward a signal processing perspective
- XAI Methods for Neural Time Series Classification: A Brief Review
Forecasting
- Counterfactual Explanations for Time Series Forecasting
- Explaining time series predictions with dynamic masks
- Series saliency: Temporal interpretation for multivariate time series forecasting
- ShapTime: A General XAI Approach for Explainable Time Series Forecasting
- TEMPORAL DEPENDENCIES IN FEATURE IMPORTANCE FOR TIME SERIES PREDICTION
- TS-MULE: Local Interpretable Model-Agnostic Explanations for Time Series Forecast Models
Classification and Regression / Forcasting
Libraries
- Time Interpret: a Unified Model Interpretability Library for Time Series
- TSGap: Composable time-series missingness simulation. Separates mechanisms (MCAR/MAR/MNAR) from patterns (pointwise/block/monotone/decay/markov)
- TSInterpret: A Python Package for the Interpretability of Time Series Classification
Showing a sample of 72 resources. View the full list on GitHub →