Application of Data Mining for Anti-money Laundering Detection: A Case Study

Abstract

Recently, money laundering is becoming more and more sophisticated, it seems to have moved from the personal gain to the cliché of drug trafficking and financing terrorism. This criminal activity poses a serious threat not only to financial institutions but also to the nation. Today, most international financial institutions have been implementing anti-money laundering solutions but traditional investigative techniques consume numerous man-hours. Besides, most of the existing commercial solutions are based on statistics such as means and standard deviations and therefore are not efficient enough, especially for detecting suspicious cases in investment activities. In this paper, we present a case study of applying a knowledge-based solution that combines data mining and natural computing techniques to detect money laundering patterns. This solution is a part of a collaboration project between our research group and an international investment bank.