OML-AD: Online Machine Learning for Anomaly Detection in Time Series Data

TL;DR

This paper introduces OML-AD, an online machine learning approach for anomaly detection in non-stationary time series, demonstrating improved accuracy and efficiency over existing methods.

Contribution

The paper presents a novel online learning-based anomaly detection method tailored for non-stationary time series, integrated into the River library.

Findings

Outperforms baseline methods in accuracy

Achieves higher computational efficiency

Effective on diverse real-world datasets

Abstract

Time series are ubiquitous and occur naturally in a variety of applications -- from data recorded by sensors in manufacturing processes, over financial data streams to climate data. Different tasks arise, such as regression, classification or segmentation of the time series. However, to reliably solve these challenges, it is important to filter out abnormal observations that deviate from the usual behavior of the time series. While many anomaly detection methods exist for independent data and stationary time series, these methods are not applicable to non-stationary time series. To allow for non-stationarity in the data, while simultaneously detecting anomalies, we propose OML-AD, a novel approach for anomaly detection (AD) based on online machine learning (OML). We provide an implementation of OML-AD within the Python library River and show that it outperforms state-of-the-art baseline methods in terms of accuracy and computational efficiency.