Using Network Analysis to Combat Money Laundering & Fraud
Money laundering and fraud cost financial institutions around the world billions annually in losses and regulatory fines. Between 2008 and 2018, nearly US$27B was paid out for AML/KYC/Sanctions fines with the average fine being US$90M.
Currently, most detection schemes rely heavily on business rules and supervised machine learning models, as well as large teams of analysts to deal with the fallout from high false positive rates – rates that are essentially inevitable due to class imbalance and garbled labeling of historical data.
Methodologies used by money launderers and fraudsters and other bad actors can often also be reframed as network analysis problems which provide potentially much better detection rates, resulting in reduced costs and limited losses. Below are some explanations of a few widely-used criminal methods, along with specific examples and ideas as to how network analysis can be applied for detection.
 “Global Financial Institutions Fined $26 Billion for AML, Sanctions & KYC Non-Compliance.” Fenergo, 9/26/2018,
Primary Stages of Money Laundering
Inserting money into legitimate financial systems in a way to hide or obfuscate the illicit origins of the funds
Creating a web of financial transactions to distance the initial depository accounts from the ultimate ownership account
Placing the laundered funds back into the economy with a perceived legitimate source
Each of these stages have specific methodologies used by money launderers that respond well to detection by network analytical techniques.
To learn more about how network analysis can help in the detection of money laundering & fraud, please fill out the form below to receive your free pdf copy of Using Network Analysis to Combat Money Laundering & Fraud by Kathryn O'Donnell.
We will not use/sell/rent your information for any mailing list, marketing ads and/or third party use. The information in this report should be reviewed only by those who are a part of the AML or AML adjacent communities.