Building a Money Laundering Network Data Base to Detect Suspicious Launderers

Dr. Lokanan received Research for Professional Development funds to conduct research on the money-laundering problems in Canada.

The purpose of this paper is to use graph technology and network analysis to identify individuals and criminal networks with linkages to Canada's financial system. Data for the project will come from newspapers, reports, cases, and commissioned hearings on money laundering in Canada, the U.S., the U.K., Europe, and Australia. The intention is to build and train an easy-to-use anti-money laundering (AML) model that law enforcement professionals and financial institutions can use to detect suspicious individuals and entities and disrupt their criminal networks. Users can use both structured and unstructured data to build supervised and unsupervised machine learning models to obtain insights and validate their money-laundering detection programs. It is hard not to see Ottawa using the findings from this project to inform Canada's AML mandates.