TS-MULE: Local Interpretable Model-Agnostic Explanations for Time Series Forecast Models

TL;DR

TS-MULE is a novel explanation method for time series forecasting models that extends LIME with specialized segmentation and perturbation techniques, improving interpretability and debugging of black-box models.

Contribution

It introduces six segmentation approaches tailored for time series to enhance local surrogate explanations, applicable across various models and datasets.

Findings

Six segmentation methods improve explanation quality

Effective across multiple deep learning architectures

Demonstrated on diverse multivariate datasets

Abstract

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.