A New Model for Evaluating Range-Based Anomaly Detection Algorithms
Classical anomaly detection (AD) is principally concerned with point-based anomalies, anomalies that occur at a single point in time. While point-based anomalies are useful, many real-world anomalies are range-based, meaning they occur over a period of time. Therefore, applying classical point-based accuracy measures to range-based AD systems can be misleading. In this paper, we present a new mathematical model that more accurately gauges the classification correctness of AD systems for range-based anomalies. Unlike prior work, our mathematical definitions are a superset of the classical AD definitions, enabling our system to also subsume point-based anomalies. Moreover, our system is broadly generalizable and provides a number of specialization functions that can control the application's bias along a multi-dimensional axis.
READ FULL TEXT