Do Deep Neural Networks Contribute to Multivariate Time Series Anomaly Detection?

TL;DR

This paper compares traditional, machine learning, and deep neural network methods for multivariate time series anomaly detection across multiple datasets, finding no single approach consistently outperforms others.

Contribution

It provides the first comprehensive comparison of conventional, machine learning, and deep neural network methods for multivariate time series anomaly detection.

Findings

No method family outperforms others across all datasets

Encourages combining different approaches in future benchmarks

Highlights the need for diverse evaluation in anomaly detection

Abstract

Anomaly detection in time series is a complex task that has been widely studied. In recent years, the ability of unsupervised anomaly detection algorithms has received much attention. This trend has led researchers to compare only learning-based methods in their articles, abandoning some more conventional approaches. As a result, the community in this field has been encouraged to propose increasingly complex learning-based models mainly based on deep neural networks. To our knowledge, there are no comparative studies between conventional, machine learning-based and, deep neural network methods for the detection of anomalies in multivariate time series. In this work, we study the anomaly detection performance of sixteen conventional, machine learning-based and, deep neural network approaches on five real-world open datasets. By analyzing and comparing the performance of each of the sixteen methods, we show that no family of methods outperforms the others. Therefore, we encourage the community to reincorporate the three categories of methods in the anomaly detection in multivariate time series benchmarks.