Precision and Recall for Range-Based Anomaly Detection
Tae J. Lee, Justin Gottschlich, Nesime Tatbul, Eric Metcalf, Stan Zdonik · arXiv (Cornell University) · 2018
Classical anomaly detection is principally concerned with point-based anomalies, anomalies that occur at a single data point. In this paper, we present a new mathematical model to express range-based anomalies, anomalies that occur over a range (or period) of time.