mlsanityData to 7 Oct 2026

Feature Importance for Time Series Data: Improving KernelSHAP

arXiv 2210.02176 ↗First posted 5 Oct 2022cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Feature importance techniques have enjoyed widespread attention in the explainable AI literature as a means of determining how trained machine learning models make their predictions. We consider Shapley value based approaches to feature importance, applied in the context of time series data. We present closed form solutions for the SHAP values of a number of time series models, including VARMAX. We also show how KernelSHAP can be applied to time series tasks, and how the feature importances that come from this technique can be combined to perform "event detection". Finally, we explore the use of Time Consistent Shapley values for feature importance.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 13 of its 23 references that are in the map. First posted on arXiv 5 Oct 2022.

Builds on

13 of 23 references.

References · 13

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  3. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  4. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  5. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  6. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  7. 2019Model-Agnostic Counterfactual Explanations for Consequential Decisionscited by 204
  8. 2015Visualizing and Understanding Recurrent Networkscited by 158
  9. 2021FastSHAP: Real-Time Shapley Value Estimationcited by 123
  10. 2017Explaining Recurrent Neural Network Predictions in Sentiment Analysiscited by 87
  11. 2020TimeSHAP: Explaining Recurrent Models through Sequence Perturbationscited by 73
  12. 2018Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMscited by 67
1 more
  1. 2021Interpretability in deep learning for finance: a case study for the Heston modelcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 0; 2026: 1.

5 papers.

  1. 2023Interpretation of Time-Series Deep Models: A Surveycited by 15
  2. 2024TimeInf: Time Series Data Contribution via Influence Functionscited by 6
  3. 2024Explaining Clustering of Ecological Momentary Assessment Data Through Temporal and Feature Attentioncited by 1
  4. 2023On the Connection between Game-Theoretic Feature Attributions and Counterfactual Explanationscited by 0
  5. 2026Autorelevance function and other feature relevance measures for univariate time seriescited by 0