One Class Splitting Criteria for Random Forests
This addresses the need for one-class classification methods in anomaly detection, providing a novel extension of Random Forests, though it is incremental as it builds on existing RF frameworks.
The paper tackles the problem of extending Random Forests to one-class classification for anomaly detection, proposing a methodology that generalizes standard splitting criteria and demonstrates relevance through an extensive benchmark against seven state-of-the-art algorithms.
Random Forests (RFs) are strong machine learning tools for classification and regression. However, they remain supervised algorithms, and no extension of RFs to the one-class setting has been proposed, except for techniques based on second-class sampling. This work fills this gap by proposing a natural methodology to extend standard splitting criteria to the one-class setting, structurally generalizing RFs to one-class classification. An extensive benchmark of seven state-of-the-art anomaly detection algorithms is also presented. This empirically demonstrates the relevance of our approach.