What is ensemble learning for anomaly detection?

Ensemble anomaly detection combines multiple detectors to improve detection robustness.

Anomaly detection ensembles combine methods like Isolation Forest, One-Class SVM, and clustering-based detectors. Each model captures different notions of anomaly. Aggregating their outputs reduces false positives and improves robustness in high-noise environments. Ensemble scoring can be done via averaging anomaly scores or majority voting.