Data mining approach to internal fraud in a project-based organization

Data mining is an efficient methodology for uncovering and extracting information from large databases, which is widely used in different areas, e.g., customer relation management, financial fraud detection, healthcare management, and manufacturing. Data mining has been successfully used in various fraud detection and prevention areas, such as credit card fraud, taxation fraud, and fund transfer fraud. However, there are insufficient researches about the usage of data mining for fraud related to internal control. In order to increase awareness of data mining usefulness in internal control, we developed a case study in a project-based organization. We analyze the dataset about working-hour claims for projects, using two data mining techniques: chi-square automatic interaction detection (CHAID) decision tree and link analysis, in order to describe characteristics of fraudulent working-hour claims and to develop a model for automatic detection of potentially fraudulent ones. Results indicate that the following characteristics of the suspected working-hours claim were the most significant: sector of the customer, origin and level of expertise of the consultant, and cost of the consulting services. Our research contributes to the area of internal control supported by data mining, with the goal to prevent fraudulent working-hour claims in project-based organizations.