Conformal k-NN Anomaly Detector for Univariate Data Streams

Vladislav Ishimtsev; Ivan Nazarov; Alexander Bernstein; Evgeny Burnaev

Conformal k-NN Anomaly Detector for Univariate Data Streams

Machine Learning 2017-06-13 v1 Data Structures and Algorithms Applications Computation Methodology

Authors: Vladislav Ishimtsev , Ivan Nazarov , Alexander Bernstein , Evgeny Burnaev

Abstract

Anomalies in time-series data give essential and often actionable information in many applications. In this paper we consider a model-free anomaly detection method for univariate time-series which adapts to non-stationarity in the data stream and provides probabilistic abnormality scores based on the conformal prediction paradigm. Despite its simplicity the method performs on par with complex prediction-based models on the Numenta Anomaly Detection benchmark and the Yahoo! S5 dataset.

Keywords

change point detection time series forecasting covariance estimation

Cite

@article{arxiv.1706.03412,
  title  = {Conformal k-NN Anomaly Detector for Univariate Data Streams},
  author = {Vladislav Ishimtsev and Ivan Nazarov and Alexander Bernstein and Evgeny Burnaev},
  journal= {arXiv preprint arXiv:1706.03412},
  year   = {2017}
}

Comments

15 pages, 2 figures, 7 tables

Related papers

View all related →

Applications · Statistics

Conformalized density- and distance-based anomaly detection in time-series data