Real-Time Anomaly Detection for Streaming Analytics
This addresses the problem of detecting anomalies in critical streaming data for applications like financial monitoring, though it appears incremental as it builds on existing HTM methods.
The paper tackles real-time anomaly detection in streaming time-series data by introducing a novel technique based on Hierarchical Temporal Memory (HTM), achieving best-in-class results on the NAB benchmark.
Much of the worlds data is streaming, time-series data, where anomalies give significant information in critical situations. Yet detecting anomalies in streaming data is a difficult task, requiring detectors to process data in real-time, and learn while simultaneously making predictions. We present a novel anomaly detection technique based on an on-line sequence memory algorithm called Hierarchical Temporal Memory (HTM). We show results from a live application that detects anomalies in financial metrics in real-time. We also test the algorithm on NAB, a published benchmark for real-time anomaly detection, where our algorithm achieves best-in-class results.