Conformal Anomaly Detection on Spatio-Temporal Observations with Missing Data
Applications
2021-06-04 v2 Methodology
Machine Learning
Abstract
We develop a distribution-free, unsupervised anomaly detection method called ECAD, which wraps around any regression algorithm and sequentially detects anomalies. Rooted in conformal prediction, ECAD does not require data exchangeability but approximately controls the Type-I error when data are normal. Computationally, it involves no data-splitting and efficiently trains ensemble predictors to increase statistical power. We demonstrate the superior performance of ECAD on detecting anomalous spatio-temporal traffic flow.
Cite
@article{arxiv.2105.11886,
title = {Conformal Anomaly Detection on Spatio-Temporal Observations with Missing Data},
author = {Chen Xu and Yao Xie},
journal= {arXiv preprint arXiv:2105.11886},
year = {2021}
}
Comments
Submitted to ICML 2021 Workshop--Distribution-free Uncertainty Quantification