Bank Checks Fraud Detection Based on the Analysis of Event Trends in Data-Flow Systems

Abstract

The paper shows trend analysis of events in data-flow systems on the example of fraud detection with not-covered checks. The analysis is based on Complex Event Processing (CEP) technology. This article proposes Algorithm 2 based on BTree and Hash type indexes for extracting a complete chain of events of any length formed by insufficient funds check deposits. The paper presents a comparison between the proposed Algorithm 2 and the existing Algorithm 1, based on the construction of event trends in the form of graphs. The average processing time of one event using the new Algorithm 2 is 56 times less with the number of events equal to 100,000. At the same time, the new Algorithm 2 processes about 900,000 events, while the existing Algorithm 1 supports only 100,000 events.