A Proposed Paradigm Using Data Mining to Minimize Online Money Laundering

Since the global financial crisis (GFC), banks have been compromised by various risks. One of the significant risks is online money laundering. It is the third-largest business in the world after currency exchange and the automotive industry. As technology has advanced, the methods of online money laundering have become more evasive. Banks' traditional methods cannot deal with online money laundering. The absence of contemporary anti-money laundering techniques has led to the rise of this criminal activity. As a result, existing systems need to be updated to accommodate the development of online money laundering. Therefore, this paper proposes and implements a paradigm (APPD-OML) based on data mining techniques like classification, clustering, and association to predict and detect online money laundering. The results indicate that the proposed paradigm outperforms each technique used separately in predicting and detecting online money laundering and outperformed the other research that used data mining in this field.