mlsanityData to 7 Oct 2026

TimeSeriesBench: An Industrial-Grade Benchmark for Time Series Anomaly Detection Models

arXiv 2402.10802 ↗First posted 16 Feb 2024cs.LGcited by 22

Not on the map. Why?

Abstract (arXiv)

Time series anomaly detection (TSAD) has gained significant attention due to its real-world applications to improve the stability of modern software systems. However, there is no effective way to verify whether they can meet the requirements for real-world deployment. Firstly, current algorithms typically train a specific model for each time series. Maintaining such many models is impractical in a large-scale system with tens of thousands of curves. The performance of using merely one unified model to detect anomalies remains unknown. Secondly, most TSAD models are trained on the historical part of a time series and are tested on its future segment. In distributed systems, however, there are frequent system deployments and upgrades, with new, previously unseen time series emerging daily. The performance of testing newly incoming unseen time series on current TSAD algorithms remains unknown. Lastly, the assumptions of the evaluation metrics in existing benchmarks are far from practical demands. To solve the above-mentioned problems, we propose an industrial-grade benchmark TimeSeriesBench. We assess the performance of existing algorithms across more than 168 evaluation settings and provide comprehensive analysis for the future design of anomaly detection algorithms. An industrial dataset is also released along with TimeSeriesBench.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 29 of its 69 references that are in the map. First posted on arXiv 16 Feb 2024.

Builds on

29 of 69 references.

References · 29

  1. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
  2. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,030
  3. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 680
  4. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 615
  5. 2018Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholdingcited by 407
  6. 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 387
  7. 2018Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applicationscited by 223
  8. 2016LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detectioncited by 213
  9. 2022TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Datacited by 211
  10. 2023FITS: Modeling Time Series with 10k Parameterscited by 185
  11. 2023TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecastingcited by 170
  12. 2019Time-Series Anomaly Detection Service at Microsoftcited by 163
17 more
  1. 2023TimeGPT-1cited by 149
  2. 2020Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progresscited by 148
  3. 2021Towards a Rigorous Evaluation of Time-series Anomaly Detectioncited by 95
  4. 2022Local Evaluation of Time Series Anomaly Detection Algorithmscited by 79
  5. 2021An Evaluation of Anomaly Detection and Diagnosis in Multivariate Time Seriescited by 68
  6. 2018Precision and Recall for Time Seriescited by 67
  7. 2020Exathlon: A Benchmark for Explainable Anomaly Detection over Time Seriescited by 56
  8. 2022TFAD: A Decomposition Time Series Anomaly Detection Architecture with Time-Frequency Analysiscited by 48
  9. 2019A Survey of Network-based Intrusion Detection Data Setscited by 46
  10. 2019MIDAS: Microcluster-Based Detector of Anomalies in Edge Streamscited by 29
  11. 2015A Meta-Analysis of the Anomaly Detection Problemcited by 23
  12. 2024Revisiting VAE for Unsupervised Time Series Anomaly Detection: A Frequency Perspectivecited by 22
  13. 2022TiSAT: Time Series Anomaly Transformercited by 15
  14. 2022Adaptive Performance Anomaly Detection for Online Service Systems via Pattern Sketchingcited by 13
  15. 2020Statistical Evaluation of Anomaly Detectors for Sequencescited by 6
  16. 2023Multivariate Time Series Anomaly Detection: Fancy Algorithms and Flawed Evaluation Methodologycited by 6
  17. 2023Beyond Sharing: Conflict-Aware Multivariate Time Series Anomaly Detectioncited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 9; 2026: 9.

22 papers.

Sort:

By area:

  1. 2025TAB: Unified Benchmarking of Time Series Anomaly Detection Methodscited by 58
  2. 2025Argos: Agentic Time-Series Anomaly Detection with Autonomous Rule Generation via Large Language Modelscited by 17
  3. 2025Time-IMM: A Dataset and Benchmark for Irregular Multimodal Multivariate Time Seriescited by 16
  4. 2026Cloud-OpsBench: A Reproducible Benchmark for Agentic Root Cause Analysis in Cloud Systemscited by 13
  5. 2025Time-RA: Towards Time Series Reasoning for Anomaly Diagnosis with LLM Feedbackcited by 7
  6. 2024TimeInf: Time Series Data Contribution via Influence Functionscited by 6
  7. 2024Peri-midFormer: Periodic Pyramid Transformer for Time Series Analysiscited by 5
  8. 2026ARFBench: Benchmarking Time Series Question Answering Ability for Software Incident Responsecited by 5
  9. 2024Anomaly Prediction: A Novel Approach with Explicit Delay and Horizoncited by 3
  10. 2026Adaptive Conformal Anomaly Detection with Time Series Foundation Models for Signal Monitoringcited by 3
  11. 2024A Scenario-Oriented Benchmark for Assessing AIOps Algorithms in Microservice Managementcited by 2
  12. 2025VISTA: Unsupervised 2D Temporal Dependency Representations for Time Series Anomaly Detectioncited by 0
10 more
  1. 2025CCE: Confidence-Consistency Evaluation for Time Series Anomaly Detectioncited by 0
  2. 2025ViTs: Teaching Machines to See Time Series Anomalies Like Human Expertscited by 0
  3. 2025A Comprehensive Forecasting-Based Framework for Time Series Anomaly Detection: Benchmarking on the Numenta Anomaly Benchmark (NAB)cited by 0
  4. 2025Fourier-KAN-Mamba: A Novel State-Space Equation Approach for Time-Series Anomaly Detectioncited by 0
  5. 2026Strong Linear Baselines Strike Back: Closed-Form Linear Models as Gaussian Process Conditional Density Estimators for TSADcited by 0
  6. 2026KairosVL: Orchestrating Time Series and Semantics for Unified Reasoningcited by 0
  7. 2026ECoLAD: Selecting Anomaly Detectors for Automotive Deployment via Compute-Reduction Evaluationcited by 0
  8. 2026Bridging Classification and Reconstruction: Cooperative Time Series Anomaly Detectioncited by 0
  9. 2026No Scale Left Behind: Multi-Scale Autoencoder with Bi-directional Attention for Time Series Anomaly Detectioncited by 0
  10. 2026Detect, Explain, Interpret: An End-to-End Benchmark for Time Series Anomaly Detection, Explainability and Interpretabilitycited by 0