Anomaly detection in time series: a comprehensive evaluation
Обнаружение аномалий во временных рядах
2022-05-01
SCID: 54.1/493nu8xk
Discuss with AI
algorithm evaluationalgorithm selectionanomalous subsequencesstate-of-the-art algorithmstime series anomaly detection
Figures from the paper
Abstract (AI)
Detecting anomalous subsequences in time series data is an important task in areas ranging from manufacturing processes over finance applications to health care monitoring. An anomaly can indicate important events, such as production faults, delivery bottlenecks, system defects, or heart flicker, and is therefore of central interest. Because time series are often large and exhibit complex patterns, data scientists have developed various specialized algorithms for the automatic detection of such anomalous patterns. The number and variety of anomaly detection algorithms has grown significantly in the past and, because many of these solutions have been developed independently and by different research communities, there is no comprehensive study that systematically evaluates and compares the different approaches. For this reason, choosing the best detection technique for a given anomaly detection task is a difficult challenge. This comprehensive, scientific study carefully evaluates most state-of-the-art anomaly detection algorithms. We collected and re-implemented 71 anomaly detection algorithms from different domains and evaluated them on 976 time series datasets. The algorithms have been selected from different algorithm families and detection approaches to represent the entire spectrum of anomaly detection techniques. In the paper, we provide a concise overview of the techniques and their commonalities; we evaluate their individual strengths and weaknesses and, thereby, consider factors, such as effectiveness, efficiency, and robustness. Our experimental results should ease the algorithm selection problem and open up new research directions.
Key Findings
1
Evaluation across 976 time-series datasets compares algorithms by effectiveness, efficiency, and robustness, addressing the lack of comprehensive benchmarking.
2
The analysis identifies individual strengths and weaknesses across detection approaches, providing evidence to guide algorithm selection for specific anomaly detection tasks.
3
The comparative study synthesizes commonalities among anomaly detection techniques and highlights directions for future research.
4
The study re-implemented and systematically evaluated 71 time-series anomaly detection algorithms spanning multiple algorithm families and application domains.
Research Object
time series data and anomalous subsequences within them
Research Subject
the effectiveness, efficiency, robustness, and comparative performance of anomaly detection algorithms for identifying anomalous subsequences
Publication Details
Publication Date
2022-05-01
Journal
Publisher
ISSN
Cited by
914
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai12
XGBoost2016
Anomaly detection: A survey2009
Isolation Forest2008
Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network2019
A Review on Outlier/Anomaly Detection in Time Series Data2021
Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications2018
Unsupervised real-time anomaly detection for streaming data2017
Multivariate Time-Series Anomaly Detection via Graph Attention Network2020
DeepAnT: A Deep Learning Approach for Unsupervised Anomaly Detection in Time Series2018
Time-Series Anomaly Detection Service at Microsoft2019
LSTM-Based VAE-GAN for Time-Series Anomaly Detection2020
Recent Advances in Anomaly Detection Methods Applied to Aviation2019