| Signature | Description | Public Member Functions |
|---|---|---|
template<typename T> struct IsoNode; template<typename T> class IsoTree; template<typename T> class IsoForest; |
Isolation Forest is an unsupervised machine learning algorithm specifically designed for anomaly detection. Instead of profiling "normal" data points, it explicitly isolates outliers by randomly selecting features and recursively partitioning the data. Because anomalies are rare and distinct, they are isolated in far fewer steps (shorter tree paths) than normal data. The algorithm is based on a tree structure (Isolation Trees) conceptually similar to Random Forest. T: Isolation-tree data type |
Isolation-tree Header File |
