What is XBOS?
Cross interaction based outlier score (XBOS) is a cluster-based algorithm for unsupervised anomaly detection. It uses k-means clustering for the first stage, and then calculate cross interaction between clusters as the second stage. Because of this second stage, A small cluster near another large cluster is treated as if that is a middle cluster, so that the data points belong to the cluster is scored ‘not so anomalous’ as a result.
XBOS assumes independence of the features as same as HBOS. XBOS shows very good performance on Kaggle credit card dataset compared to Isolation Forest and HBOS.
XBOS is a really simple algorithm and implemented in just 55 lines of Python code.