Anomaly Detection in Streams with Extreme Value Theory

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. Here, we propose a new approach to detect outliers in streaming univariate time series based on Extreme Value Theory that does not require to hand-set thresholds and makes no assumption on the distribution: the main parameter is only the risk, controlling the number of false posi-tives. Our approach can be used for outlier detection, but more generally for automatically setting thresholds, making it useful in wide number of situations. We also experiment our algorithms on various real-world datasets which confirm its soundness and efficiency.
Complete list of metadatas

Cited literature [23 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01640325
Contributor : Alexandre Termier <>
Submitted on : Monday, November 20, 2017 - 5:33:09 PM
Last modification on : Monday, April 1, 2019 - 12:45:21 PM
Long-term archiving on : Wednesday, February 21, 2018 - 2:12:47 PM

File

siffer_kdd_17.pdf
Files produced by the author(s)

Identifiers

Citation

Alban Siffer, Pierre-Alain Fouque, Alexandre Termier, Christine Largouët. Anomaly Detection in Streams with Extreme Value Theory. KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Aug 2017, Halifax, Canada. ⟨10.1145/3097983.3098144⟩. ⟨hal-01640325⟩

Share

Metrics

Record views

960

Files downloads

1805