Time series anomaly detection advances unified framework and evaluation insights
Future of Time Series Anomaly Detection: From Historical Review to Unified Outlook
Machine LearningArtificial Intelligence
Summary
Time series anomaly detection is about finding unusual patterns in data that changes over time. The authors review new methods like language models and diffusion models, which are more complex than older methods. They organize these approaches into clear categories, test how well evaluation metrics work, and share tools for comparing detection methods. They also point out open challenges to help future researchers improve these systems.
What this means in practice
- •For data engineering teams: Use the unified taxonomy and benchmark tools to select and compare anomaly detection models reliably for complex time series data.
- •For cloud platform developers: Integrate comprehensive evaluation frameworks for time series anomaly detection to improve monitoring services across different data domains.
A survey. It maps existing work.
Authors
Zhijie Zhong, Zhiwen Yu, Pengyu Li, Liujian Zhang, Qiaoli Ni, Jiang Jun, Jianming Lv, Kaixiang Yang, C. L. Philip Chen
Abstract
Time series anomaly detection (TSAD) is a foundational problem in data mining, aiming to identify observations that deviate significantly from nominal temporal patterns. Driven by escalating data volumes and application complexity, recent research has yielded diverse architectures, including diffusion models, state space models, and large language models (LLMs). However, existing surveys provide limited coverage of these emerging designs and lack a unified treatment of multivariate anomalies, cross-domain unified modeling, metric reliability, and contemporary evaluation challenges. To bridge these gaps, this survey delivers three core contributions: (1) We establish a refined anomaly categorization and a structured taxonomy of paradigms reflecting modern advances, comparing detection mechanisms and charting developmental trajectories across paradigms. (2) We provide an extensive analysis of evaluation methodologies and conduct comprehensive experiments to assess metric fidelity, complemented by an open-source benchmark repository encompassing algorithms, datasets, and evaluation tools. (3) We outline key open challenges, offering forward-looking perspectives on dynamic thresholding, model interpretability, zero-shot transfer, multi-modal alignment, and foundational models for time series. By addressing existing theoretical and empirical limitations, this survey establishes a coherent framework to guide future TSAD research and practical deployments.