Skip to content

SHAP for Time Series Foundation Models

Home / Concepts / SHAP for Time Series Foundation Models

SHAP for Time Series Foundation Models

Auto-generated stub. Edit this file to add more details.

An algorithm for computing SHAP values for time series foundation models by exploiting their inherent flexibility in input context length and covariate handling.

Why It Matters

Addresses the critical need for explainability in black-box foundation models applied to high-stakes infrastructure like power grids.

Evidence

propose an efficient algorithm for computing Shapley Additive Explanations (SHAP) tailored to these models. The proposed approach leverages the flexibility of TSFMs with respect to input context length and provided covariates.

Metadata & Links