The stability of the economy and political system of any country highly depends on the policy of anti-money laundering (AML). If government policies are incapable of handling money laundering activities in an appropriate way, the control of the economy can be transferred to criminals. The current literature provides various technical solutions, such as clustering-based anomaly detection techniques, rule-based systems, and a decision tree algorithm, to control such activities that can aid in identifying suspicious customers or transactions. However, the literature provides no effective and appropriate solutions that could aid in identifying relationships between suspicious customers or transactions. The current challenge in the field is to identify associated links between suspicious customers who are involved in money laundering. To consider this challenge, this paper discusses the challenges associated with identifying relationships such as business and family relationships and proposes a model to identify links between suspicious customers using social network analysis (SNA). The proposed model aims to identify various mafias and groups involved in money laundering activities, thereby aiding in preventing money laundering activities and potential terrorist financing. The proposed model is based on relational data of customer profiles and social networking functions metrics to identify suspicious customers and transactions. A series of experiments are conducted with financial data, and the results of these experiments show promising results for financial institutions who can gain real benefits from the proposed model.

No abstract