# Time Series Anomaly Detection; Detection of anomalous drops with limited features and sparse examples in noisy highly periodic data

arXiv: https://arxiv.org/abs/1708.03665 · HTML: https://mlsanity.com/paper/1708.03665/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Aug 2017.

## Built on by (most cited first, 12 of 12)

- [Neural Contextual Anomaly Detection for Time Series](https://mlsanity.com/paper/2107.07702/) (2021)
- [MST-GAT: A Multimodal Spatial-Temporal Graph Attention Network for Time Series Anomaly Detection](https://mlsanity.com/paper/2310.11169/) (2023)
- [Online false discovery rate control for anomaly detection in time series](https://mlsanity.com/paper/2112.03196/) (2021)
- [Machine Learning on Dynamic Graphs: A Survey on Applications](https://mlsanity.com/paper/2401.08147/) (2024)
- [Addressing Out-of-Label Hazard Detection in Dashcam Videos: Insights from the COOOL Challenge](https://mlsanity.com/paper/2501.16037/) (2025)
- [Anomaly Detection in Beehives: An Algorithm Comparison](https://mlsanity.com/paper/2110.03945/) (2021)
- [Monte Carlo EM for Deep Time Series Anomaly Detection](https://mlsanity.com/paper/2112.14436/) (2021)
- [A Semi-Supervised Approach for Abnormal Event Prediction on Large Operational Network Time-Series Data](https://mlsanity.com/paper/2110.07660/) (2021)
- [DeCorus: Hierarchical Multivariate Anomaly Detection at Cloud-Scale](https://mlsanity.com/paper/2202.06892/) (2022)
- [Practical data monitoring in the internet-services domain](https://mlsanity.com/paper/2203.08067/) (2022)
- [AlerTiger: Deep Learning for AI Model Health Monitoring at LinkedIn](https://mlsanity.com/paper/2306.01977/) (2023)
- [Low-count Time Series Anomaly Detection](https://mlsanity.com/paper/2308.12925/) (2023)

## Abstract (arXiv)

Google uses continuous streams of data from industry partners in order to deliver accurate results to users. Unexpected drops in traffic can be an indication of an underlying issue and may be an early warning that remedial action may be necessary. Detecting such drops is non-trivial because streams are variable and noisy, with roughly regular spikes (in many different shapes) in traffic data. We investigated the question of whether or not we can predict anomalies in these data streams. Our goal is to utilize Machine Learning and statistical approaches to classify anomalous drops in periodic, but noisy, traffic patterns. Since we do not have a large body of labeled examples to directly apply supervised learning for anomaly classification, we approached the problem in two parts. First we used TensorFlow to train our various models including DNNs, RNNs, and LSTMs to perform regression and predict the expected value in the time series. Secondly we created anomaly detection rules that compared the actual values to predicted values. Since the problem requires finding sustained anomalies, rather than just short delays or momentary inactivity in the data, our two detection methods focused on continuous sections of activity rather than just single points. We tried multiple combinations of our models and rules and found that using the intersection of our two anomaly detection methods proved to be an effective method of detecting anomalies on almost all of our models. In the process we also found that not all data fell within our experimental assumptions, as one data stream had no periodicity, and therefore no time based model could predict it.