Unsupervised Statistical Tools for Anomaly Detection: The Case of Healthcare Frauds

Fabrizio RUGGERI
Senior Fellow at the Italian National Research Council in Milano

The research is motivated by the increased interest in detecting possible frauds in healthcare systems. We propose some unsupervised statistical tools (Lorenz curve, concentration function, sum of ranks, Gini and Pietra indices) to provide efficient and easy-to-use methods  aimed to signal possible anomalous behaviours. A more sophisticated  method, based on Bayesian co-clustering, is presented as well.