Proposal / Submission Type
Peer Reviewed Paper
Location
Richmond, Virginia
Start Date
11-6-2013 9:30 AM
Abstract
Money launderers hide traces of their transactions with the involvement of entities that participate in sophisticated schemes. Money laundering detection requires unraveling concealed connections among multiple but seemingly unrelated human money laundering networks, ties among actors of those schemes, and amounts of funds transferred among those entities. The link among small networks, either financial or social, is the primary factor that facilitates money laundering. Hence, the analysis of relations among money laundering networks is required to present the full structure of complex schemes. We propose a framework that uses sequence matching, case-based analysis, social network analysis, and complex event processing to detect money laundering. Our framework captures an ongoing single scheme as an event, and associations among such ongoing sequence of events to capture complex relationships among evolving money laundering schemes. The framework can detect associated multiple money laundering networks even in the absence of some evidence. We validated the accuracy of detecting evolving money laundering schemes using a multi-phases test methodology. Our test used data generated from real-life cases, and extrapolated to generate more data from real-life schemes generator that we implemented.
Keywords: Anti Money Laundering, Social Network Analysis, Complex Event Processing
Scholarly Commons Citation
Mehmet, Murad; Wijesekera, Duminda; and Buchholtz, Miguel F., "Money Laundering Detection Framework to Link the Disparate and Evolving Schemes" (2013). Annual ADFSL Conference on Digital Forensics, Security and Law. 11.
https://commons.erau.edu/adfsl/2013/tuesday/11
Included in
Computer Engineering Commons, Computer Law Commons, Electrical and Computer Engineering Commons, Forensic Science and Technology Commons, Information Security Commons
Money Laundering Detection Framework to Link the Disparate and Evolving Schemes
Richmond, Virginia
Money launderers hide traces of their transactions with the involvement of entities that participate in sophisticated schemes. Money laundering detection requires unraveling concealed connections among multiple but seemingly unrelated human money laundering networks, ties among actors of those schemes, and amounts of funds transferred among those entities. The link among small networks, either financial or social, is the primary factor that facilitates money laundering. Hence, the analysis of relations among money laundering networks is required to present the full structure of complex schemes. We propose a framework that uses sequence matching, case-based analysis, social network analysis, and complex event processing to detect money laundering. Our framework captures an ongoing single scheme as an event, and associations among such ongoing sequence of events to capture complex relationships among evolving money laundering schemes. The framework can detect associated multiple money laundering networks even in the absence of some evidence. We validated the accuracy of detecting evolving money laundering schemes using a multi-phases test methodology. Our test used data generated from real-life cases, and extrapolated to generate more data from real-life schemes generator that we implemented.
Keywords: Anti Money Laundering, Social Network Analysis, Complex Event Processing
