Screen Shot 2018-11-13 at 11.00.07 AM


Detecting Fraud and Money Laundering in Real-Time with a Graph Database Part 2

Recorded SEPTEMBER 26, 2018 

This is the 4th episode that continues TigerGraph's Graph Guru series, a free educational webinar series for developers and data scientists.

Money laundering is the act of concealing the transformation of profits from illegal activities and corruption into ostensibly "legitimate" assets. Almost every bank has an Anti-Money Laundering (AML) department to generate SARs (Suspicious Activity Reports) daily. Failure to properly monitor transactions of money-laundering is a serious compliance issue, which could result in huge fines. For example, Commonwealth Bank of Australia was fined $700 million for AML non-compliance. It isn’t alone-- U.S. Bancorp was fined $613 million in February 2018 by U.S. authorities for lax anti-money laundering controls.

Regulations are enforced to capture money laundering from corrupted politicians, drug cartels, to small tax cheats and alimony deadbeats etc. In this episode, we will detail a graph solution to detect a structure (often known as smurfing) money laundering pattern. In this episode we will: 

  • Explain smurfing and how criminals use this pattern to bypass SARs.
  • Present a graph solution to capture such money laundering patterns using GSQL.
  • Review a real-life business case and discuss in depth to show the flexibility and suitability of GSQL in AML domain.

Attendees will receive links for the synthetic dataset as well as graph queries built for a typical AML smurfing case. 


Gaurav Deshpande, VP of Marketing, TigerGraph 

Dr. Dan Hu - Lead Software Engineer, TigerGraph