mTSBench: Benchmarking Multivariate Time Series Anomaly Detection and Model Selection at Scale

2025-06-26 · Xiaona Zhou, Constantin Brif, Ismini Lourentzou

Multivariate time series anomaly detection (MTS-AD) is critical in domains like healthcare, cybersecurity, and industrial monitoring, yet remains challenging due to complex inter-variable dependencies, temporal dynamics, and sparse anomaly labels. We introduce mTSBench, the largest benchmark to date for MTS-AD and unsupervised model selection, spanning 344 labeled time series across 19 datasets and 12 diverse application domains. mTSBench evaluates 24 anomaly detection methods, including large language model (LLM)-based detectors for multivariate time series, and systematically benchmarks unsupervised model selection techniques under standardized conditions. Consistent with prior findings, our results confirm that no single detector excels across datasets, underscoring the importance of model selection. However, even state-of-the-art selection methods remain far from optimal, revealing critical gaps. mTSBench provides a unified evaluation suite to enable rigorous, reproducible comparisons and catalyze future advances in adaptive anomaly detection and robust model selection.

📄 PDF Abstract BibTeX arXiv:2506.21550

Code (1)

plan-lab/mtsbench 공식 구현 pytorch

Tasks

Anomaly Detection BenchmarkingLanguage ModelingLanguage ModellingLarge Language ModelModel SelectionTime SeriesTime Series Anomaly Detection

CRAFTIIF: Cross-Resolution Analytic Four-Type Interpretable Isolation Forest for Multivariate Time Series Anomaly Detection

2026-06-11 · William Smits arxiv

Anomaly detection in multivariate time series is challenged by four structurally distinct anomaly types -- point (isolated spikes), distributional (level shifts), temporal (rhythm changes), and collective (inter-sensor c…

Time Series Anomaly Detection

Benchmarking Unsupervised Strategies for Anomaly Detection in Multivariate Time Series

2025-06-25 · Laura Boggia, Rafael Teixeira de Lima, Bogdan Malaescu

Anomaly detection in multivariate time series is an important problem across various fields such as healthcare, financial services, manufacturing or physics detector monitoring. Accurately identifying when unexpected err…

Anomaly Detection Benchmarking Time Series Time Series Anomaly Detection

Fun-TSG: A Function-Driven Multivariate Time Series Generator with Variable-Level Anomaly Labeling

2026-04-14 · Pierre Lotte, André Péninou, Olivier Teste arxiv

Reliable evaluation of anomaly detection methods in multivariate time series remains an open challenge, largely due to the limitations of existing benchmark datasets. Current resources often lack fine-grained anomaly ann…

Anomaly Detection

Federated Learning for Multivariate Time Series Anomaly Detection in Industrial Automation

2026-05-26 · Khayyam Nosrati, Martin Uray, Saverio Messineo, Olaf Sassnick 외 arxiv

Federated learning (FL) has broadened the horizon for multivariate time series anomaly detection (MTSAD). However, benchmarking such anomaly detection methods within FL paradigm poses data-centric challenges. The existin…

Time Series Anomaly Detection Federated Learning

Entropy Causal Graphs for Multivariate Time Series Anomaly Detection

2023-12-15 · Falih Gozi Febrinanto, Kristen Moore, Chandra Thapa, Mujie Liu 외

Many multivariate time series anomaly detection frameworks have been proposed and widely applied. However, most of these frameworks do not consider intrinsic relationships between variables in multivariate time series da…

Anomaly Detection Time Series Time Series Anomaly Detection