Unsupervised Anomaly Detection in Time-series: An Extensive Evaluation and Analysis of State-of-the-art Methods

TL;DR

This paper provides a comprehensive evaluation of recent unsupervised time-series anomaly detection methods, incorporating new metrics and protocols to assess their practical relevance and robustness in real-world scenarios.

Contribution

It introduces an extensive evaluation framework that considers model size, stability, and anomaly types, offering deeper insights into the applicability of state-of-the-art methods.

Findings

Enhanced performance metrics tailored for time-series

Insights into model stability and size impacts

Analysis of method effectiveness across different anomaly types

Abstract

Unsupervised anomaly detection in time-series has been extensively investigated in the literature. Notwithstanding the relevance of this topic in numerous application fields, a comprehensive and extensive evaluation of recent state-of-the-art techniques taking into account real-world constraints is still needed. Some efforts have been made to compare existing unsupervised time-series anomaly detection methods rigorously. However, only standard performance metrics, namely precision, recall, and F1-score are usually considered. Essential aspects for assessing their practical relevance are therefore neglected. This paper proposes an in-depth evaluation study of recent unsupervised anomaly detection techniques in time-series. Instead of relying solely on standard performance metrics, additional yet informative metrics and protocols are taken into account. In particular, (i) more elaborate performance metrics specifically tailored for time-series are used; (ii) the model size and the model stability are studied; (iii) an analysis of the tested approaches with respect to the anomaly type is provided; and (iv) a clear and unique protocol is followed for all experiments. Overall, this extensive analysis aims to assess the maturity of state-of-the-art time-series anomaly detection, give insights regarding their applicability under real-world setups and provide to the community a more complete evaluation protocol.