Anomaly Detection in Streams with Extreme Value Theory

Alban Siffer, Pierre-Alain Fouque, Alexandre Termier, Christine Largouët

2017 · 517 citations · 24 references

DOIFull text

Open access

Concepts

Abstract

Anomaly detection in time series has attracted considerable attention due to its importance in many real-world applications including intrusion detection, energy management and finance. Most approaches for detecting outliers rely on either manually set thresholds or assumptions on the distribution of data according to Chandola, Banerjee and Kumar.

References

24