TS-MULE: Local Interpretable Model-Agnostic Explanations for Time Series Forecast Models
This provides interpretability for time series forecasting in domains like weather or failure prediction, but it is incremental as it builds on existing LIME methods.
The paper tackled the problem of interpreting black-box time series forecast models by proposing TS-MULE, a local surrogate explanation method that extends LIME with six segmentation approaches, and demonstrated its performance on three deep learning models and three datasets.
Time series forecasting is a demanding task ranging from weather to failure forecasting with black-box models achieving state-of-the-art performances. However, understanding and debugging are not guaranteed. We propose TS-MULE, a local surrogate model explanation method specialized for time series extending the LIME approach. Our extended LIME works with various ways to segment and perturb the time series data. In our extension, we present six sampling segmentation approaches for time series to improve the quality of surrogate attributions and demonstrate their performances on three deep learning model architectures and three common multivariate time series datasets.