Reviews: Precision and Recall for Time Series

Summary: The authors present a parameterized model that generalizes precision and recall to "range-based" anomaly detection. A range-based anomaly is defined as "an anomaly that occurs over a consecutive sequence of time points, where no non-anomalous data points exist between the beginning and the end of the anomaly". The model is carefully and precisely defined. Then it is evaluated by comparing it against the metric proposed in the Numenta Anomaly Benchmark. The authors conclude that their metric is superior to the NAB metric.