Analysis of Performance Anomaly and Fraudster Profile for Fraud Prevention and Detection

Abstract

The rapid development of technology provides us with a lot of data that can be used for various purposes, such as fraud risk management. Data analytics should be the basis for anti-fraud activities related to prevention and detection processes. This study aims to elaborate on the data analytics used in developing fraud red flags based on historical reports. By applying anomaly data analytics and demographic profiles of fraudsters, this study finds that performance anomalies contribute 68% to fraud, while 3 to 10 years of service without career advancement can trigger motivation to commit fraud. Finally, the paper recommends that data analytics should be followed by human approaches such as lifestyle audits and career advancement programs. Further research is expected to be able to complement other parameters for data analysis and use statistical methods to obtain more accurate results.