# Refining the Optimization Target for Automatic Univariate Time Series Anomaly Detection in Monitoring Services

arXiv: https://arxiv.org/abs/2307.10653 · HTML: https://mlsanity.com/paper/2307.10653/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 34 references that are in the map.
- First posted on arXiv 20 Jul 2023.

## Builds on (most cited first, 9 of 9)

- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [Are Transformers Effective for Time Series Forecasting?](https://mlsanity.com/paper/2205.13504/) (2022)
- [Imaging Time-Series to Improve Classification and Imputation](https://mlsanity.com/paper/1506.00327/) (2015)
- [TODS: An Automated Time Series Outlier Detection System](https://mlsanity.com/paper/2009.09822/) (2020)
- [Real-Time Anomaly Detection and Localization in Crowded Scenes](https://mlsanity.com/paper/1511.06936/) (2015)
- [Automated Model Selection for Time-Series Anomaly Detection](https://mlsanity.com/paper/2009.04395/) (2020)
- [cleanTS: Automated (AutoML) Tool to Clean Univariate Time Series at Microscales](https://mlsanity.com/paper/2110.11815/) (2021)
- [MOSPAT: AutoML based Model Selection and Parameter Tuning for Time Series Anomaly Detection](https://mlsanity.com/paper/2205.11755/) (2022)
- [Self-supervised learning for fast and scalable time series hyper-parameter tuning](https://mlsanity.com/paper/2102.05740/) (2021)

## Abstract (arXiv)

Time series anomaly detection is crucial for industrial monitoring services that handle a large volume of data, aiming to ensure reliability and optimize system performance. Existing methods often require extensive labeled resources and manual parameter selection, highlighting the need for automation. This paper proposes a comprehensive framework for automatic parameter optimization in time series anomaly detection models. The framework introduces three optimization targets: prediction score, shape score, and sensitivity score, which can be easily adapted to different model backbones without prior knowledge or manual labeling efforts. The proposed framework has been successfully applied online for over six months, serving more than 50,000 time series every minute. It simplifies the user's experience by requiring only an expected sensitive value, offering a user-friendly interface, and achieving desired detection results. Extensive evaluations conducted on public datasets and comparison with other methods further confirm the effectiveness of the proposed framework.