Detecting and Preventing Fraud with Data Analytics

Abstract Although fraud is not a new issue, the current financial crisis has enlightened that fraud occurs mainly during a recession, as compared with normal periods of economic growth. In counterbalance to the slow economic recovery, managers need to start a series of antifraud measures, as a leverage of cost control, while reducing available resources. Fraud involves inclusively significant financial risks which may threaten profitability, and the image of an economic entity. In these circumstances, in which development of the IT systems plays a central role in the creation of competitive companies, the amount of processed data has grown exponentially. Internal control team members should need to look at every transaction that takes place, but, unfortunately this issue can no longer be manually performed, requiring the use of data analysis tools and programs. Since the companies usually operate with large volumes of data, it is absolutely necessary to implement such processes of continuous monitoring, in order to identify anomalies in the data stream or behavioral patterns, potentially fraudulent. Such new and significant information will be later used in directing investigations, as well as to make recommendations to improve the control activities. We strive to provide an overview of the way in which technology can be implemented to improve fraud prevention and detection, inside of a public or private economic entity.