Anomaly Detection under Cost Constraint

Abstract

Anomaly detection is commonly used in fraud analysis. However, budget constraints can turn the audit process unfeasible when a sizable number of anomalies are identified. We propose a method to select cases probabilistically based on their impact, but guaranteeing that the relative discrepancy between the observed values and the expected behaviour are also taken into account. We apply the proposed method to a project designed to monitor the Brazilian public health care payment system in search for fraudulent behaviour.