Interpreting Outliers in Time Series Data through Decoding Autoencoder

TL;DR

This paper presents a novel approach for interpreting outliers in manufacturing time series data using autoencoders combined with multiple XAI techniques and introduces AEE, an ensemble method for more comprehensive explanations.

Contribution

It introduces AEE, a new ensemble method that fuses multiple XAI explanations for autoencoders, enhancing interpretability of outliers in time series data.

Findings

A new quantitative method for evaluating explanation quality.

Effective outlier explanations validated by domain experts.

A comprehensive framework combining autoencoders and XAI techniques.

Abstract

Outlier detection is a crucial analytical tool in various fields. In critical systems like manufacturing, malfunctioning outlier detection can be costly and safety-critical. Therefore, there is a significant need for explainable artificial intelligence (XAI) when deploying opaque models in such environments. This study focuses on manufacturing time series data from a German automotive supply industry. We utilize autoencoders to compress the entire time series and then apply anomaly detection techniques to its latent features. For outlier interpretation, we (i) adopt widely used XAI techniques to the autoencoder's encoder. Additionally, (ii) we propose AEE, Aggregated Explanatory Ensemble, a novel approach that fuses explanations of multiple XAI techniques into a single, more expressive interpretation. For evaluation of explanations, (iii) we propose a technique to measure the quality of encoder explanations quantitatively. Furthermore, we qualitatively assess the effectiveness of outlier explanations with domain expertise.