Conformal Anomaly Detection on Spatio-Temporal Observations with Missing Data
arXiv:2105.11886
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.
Submitted to ICML 2021 Workshop--Distribution-free Uncertainty Quantification
References in corpus (5)
- Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery
- Real-Time Illegal Parking Detection System Based on Deep Learning
- Conformalized Quantile Regression
- Conformal k-NN Anomaly Detector for Univariate Data Streams
- Online control of the false discovery rate with decaying memory