TsSHAP: Robust model agnostic feature-based explainability for time series forecasting
This addresses the problem of interpretability in time series forecasting for users needing trustworthy AI, though it is incremental as it adapts existing SHAP methods to a new domain.
The paper tackles the lack of explainability methods for time series forecasting by proposing TsSHAP, a model-agnostic feature-based algorithm that provides explanations for any black-box forecasting model using SHAP values, validated through extensive experiments on multiple datasets.
A trustworthy machine learning model should be accurate as well as explainable. Understanding why a model makes a certain decision defines the notion of explainability. While various flavors of explainability have been well-studied in supervised learning paradigms like classification and regression, literature on explainability for time series forecasting is relatively scarce. In this paper, we propose a feature-based explainability algorithm, TsSHAP, that can explain the forecast of any black-box forecasting model. The method is agnostic of the forecasting model and can provide explanations for a forecast in terms of interpretable features defined by the user a prior. The explanations are in terms of the SHAP values obtained by applying the TreeSHAP algorithm on a surrogate model that learns a mapping between the interpretable feature space and the forecast of the black-box model. Moreover, we formalize the notion of local, semi-local, and global explanations in the context of time series forecasting, which can be useful in several scenarios. We validate the efficacy and robustness of TsSHAP through extensive experiments on multiple datasets.