Isolation forest (original) (raw)

Isolation Forest is an algorithm for data anomaly detection. It detects anomalies using isolation (how far a data point is from the rest of the data), rather than modeling the normal points. It was initially developed by Fei Tony Liu and Zhi-Hua Zhou in 2007. The significance of his research lies in its deviation from the mainstream philosophy underpinning most existing anomaly detectors at the time, where all the normal instances are profiled before anomalies are identified as instances that do not conform to the distribution of the normal instances. Isolation forest introduces a different method that explicitly isolates anomalies using binary trees, demonstrating a new possibility of a faster anomaly detector that directly targets anomalies without profiling all the normal instances. The