Temporal Dependencies in Feature Importance for Time Series Predictions

1 code implementation • 29 Jul 2021 • Kin Kwan Leung, Clayton Rooke, Jonathan Smith, Saba Zuberi, Maksims Volkovs

Time series data introduces two key challenges for explainability methods: firstly, observations of the same feature over subsequent time steps are not independent, and secondly, the same feature can have varying importance to model predictions over time.

Feature Importance Time Series +1