Anomaly and fraud detection based on social services data in the sphere of digital economy

The article is devoted to the study of the anomaly and fraud detection problem in the data from social services. The problem of detecting anomalies is extremely relevant for data-based processes in the digital economy. In this paper, we propose a two-step approach for the phased detection of anomalies using auto-encoders and the contingency criterion. An experimental study of the efficiency of the proposed algorithms was conducted on an open test data set.