White Paper: Knowledge Graphs for Anti-Money Laundering and Transaction Monitoring
Today’s anti-money laundering (AML) and transaction monitoring systems need to be quicker and more agile to identify increasingly complex fraudulent transactions. Due to rapid evolution of fraudulent behavior, often layered behind seemingly innocuous transactions, AML models require greater sophistication to remain effective. Flexible approaches that utilize advanced computational techniques are needed to adapt to changing fraud patterns and to create effective rules for detection.
Current AML and transaction monitoring efforts may be insufficient for the following reasons:
- The global nature of today’s financial networks creates complex, high-dimensional, non-linear patterns.
- Rules based approaches do not scale well and produce high false positive rates.
- Fraudulent behavior is deeply hidden behind innocuous behavior due to complicated account layering.
- If transaction monitoring is based on historical patterns of behavior, it will fail to identify a new fraudulent behavior until it is too late to act.
In December of 2018, the Federal Reserve, Federal Deposit Insurance Corporation (FDIC), Financial Crimes Enforcement Network (FinCEN), National Credit Union Administration and Office of the Comptroller of the Currency (OCC), issued the Joint Statement on Innovative Efforts to Combat Money Laundering and Terrorist Financing. The Joint Statement encourages banks to implement innovative approaches, specifically referencing artificial intelligence (AI). The document states that financial Institutions need to become increasingly sophisticated in their approaches to identifying suspicious activity by building innovative internal financial intelligence units devoted to identifying complex and strategic illicit finance vulnerabilities and threats.
Knowledge Graphs have emerged as an important tool for AML and transaction monitoring. As money laundering involves cash flow relationships between entities, a Knowledge Graph can be used to capture financial transactions. In our Whitepaper, we demonstrate two graph analytics techniques, clustering and label propagation. Clustering can be used to focus investigation on certain high-risk sectors, while simultaneously reducing focus on low-risk sectors. This provides an efficient allocation of analyst resources and reduces false positives. Label propagation helps find previously unknowable patterns that may have been missed by analysts in the transaction monitoring process, thereby reducing false negatives.
Download our Whitepaper for more information about:
- Knowledge Graph technologies for effective for AML and transaction monitoring
- Using clustering and label propagation to reduce false positives and false negatives
- Integrating Knowledge Graph platforms with existing AML operational systems
To download, please fill out the form below to receive a copy: