Data Mining Techniques for Anti Money Laundering

摘要

Money Laundering is the process of creating the appearance that large amounts of money obtained from serious crimes, such as drug trafficking or terrorist activity, originated from a legitimate source. Through money laundering, the launderer transforms the monetary proceeds derived from criminal activity into funds with an apparently legal source. The system that works against Money laundering is Anti-Money Laundering (AML) system. The existing system for Anti-Money Laundering accepts the bulk of data and converts it to large volumes reports that are tedious and topsy-turvy for a person to read without any help of software. To develop a structure to research in datamining, we create a taxonomy that combines research on patterns of observed fraud schemes with an appreciation of areas that benefit from a productive application of data mining. The aim of this study was to review research conducted in the field of fraud detection with an emphasis on detecting honey laundering and examine deficiencies based on data mining techniques. Which include a set of predefined rules and threshold values. In addition to this approach, data mining techniques are very convenient to detest money laundering patterns and detect unusual behavior. Therefore, unsupervised data mining technique will be more effective to detect new patterns of money laundering and can be crucial to enhance learning models based on classification methods. Of course, the development of new methods will be very useful to increase the accuracy of performance.