Generic and Scalable Framework for Automated Time-series Anomaly Detection

By Nikolay Pavlovich Laptev, Saeed Amizadeh, Ian Flint. Knowledge Discovery and Data Mining, 2015

482 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications, Signal Processing

View Paper: https://www.semanticscholar.org/paper/435c170edd031b65cf9087cf3c8473f071477df5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Networks and Communications

In Signal Processing

Citations in the corpus

Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications (2018, methodology): “Both EGADS and Opprentice showed promising results, but they heavily rely on good labels (much more than the anecdotal labels accumulated in our context), which is generally not feasible in large scale applications.”
Evaluating Real-Time Anomaly Detection Algorithms -- The Numenta Anomaly Benchmark (2015, methodology): “There are, of course, many algorithms we have not directly tested [2, 9-14].”
DeepAnT: A Deep Learning Approach for Unsupervised Anomaly Detection in Time Series (2019, methodology): “On a detailed level, Table 2 shows a comparison of DeepAnTwith EGADS, Twitter, and LSTM (DeepAnT using LSTM as a predictor) on the whole data set.”
Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network (2019, background): “Industry devices, such as server machines [9, 14], spacecrafts [6], robot-assisted systems [16, 17], engines [11], are typically monitored with multiple time series metrics (also called telemetry data, sensor data, etc.”
Unsupervised real-time anomaly detection for streaming data (2017, methodology): “Yahoo released a dataset for anomaly detection in time-series data [8], but it is not available outside of academia and does not incorporate the requirements of streaming applications.”
Smart Anomaly Detection in Sensor Systems (2020, methodology): “Yahoo Webscope [33] includes a labeled anomaly detection dataset released by Yahoo Labs consisting of time series (both real and synthetic) with tagged anomaly points.”
Multivariate Time-series Anomaly Detection via Graph Attention Network (2020, methodology): “1) Forecasting-based Models: A forecasting-based model detects anomalies based on prediction errors [22].”
A Review on Outlier/Anomaly Detection in Time Series Data (2020, background): “[2008, 2009] Estimation Multivariate ✗ ✗ A Li et al. [2009] Dissimilarity Univariate ✓ ✓ O Sakurada and Yairi [2014] Estimation Multivariate ✗ ✗ A Zhou et al.”
Time-Series Anomaly Detection Service at Microsoft (2019, methodology): “For instance, Yahoo releases EGADS [11] to automatically monitor and raise alerts on millions of time-series of different Yahoo properties for various use-cases.”