Data Analytics to Detect Evolving Money Laundering

Money laundering evolves using multiple layers of trade, multi trading methods and uses multiple components in order to evade detection and prevention techniques. Consequently, detecting money laundering requires an analytical framework that can handle large amounts of unstructured, semistructured and transactional data that stream at transactional speeds to detect business-complexities, and discover deliberately concealed relationships. Based on our prior work and a static risk model proposed in the Bank Security Act, we propose a dynamic risk model that assigns a risk score for every transaction being a potential component of a larger money-laundering scheme. We use social networks to connect missing links in such potential transaction sequences. Taken together we can provide a financial sector independent risk assessment to submitted transactions. The proposed risk model is validated using data from realistic scenarios and our already developed money laundering evolution detection framework (MLEDF) that we developed earlier using sequence matching, case-based analysis, social networks, and complex event processing to link fraudulent transaction trails. MLEDF has components to collect data, run them against business rules and evolution models, run detection algorithms and use social network analysis to connect potential participants. Keyword: Data Analytics; Social network analysis; Anti Money Laundering; Dynamic Risk Model ; Money laundering Risk .