Today, many financial institutions find that their traditional anti-money laundering (AML) transaction monitoring systems are insufficient when relied on to detect risk in financial markets. In short, they fail to enrich, connect, or operationalize the various forms of data associated with such markets, often causing investigators to miss suspicious patterns of behavior that may exist within this data. Similarly, these legacy approaches overburden investigators with exceptionally high volumes of false positive alerts, making the process of detecting risks related to financial crime to be both inefficient and ineffective.

 

Now, industry expert Scott Nathan, Head of Innovation for AML and Risk at State Street, has been working with Quantexa on a new approach to AML in markets, one that harnesses contextual decision intelligence for more efficient and effective risk detection in financial markets.

 

Something Had to Be Done

Recent money laundering cases have resulted in fines approaching a billion dollars for numerous tier one banks. In these cases, the critical factor was the relationships between both sides of the trades. Using a rule-based approach, financial institutions may capture one or more of the trades associated with a scheme yet fail to act on them because the institution lacks context around those trades.

 

Conversely, using contextual monitoring that leverages entity resolution, network analytics, and advanced analytics offers a new approach to generating insights that empower decision making. Using this approach, financial institutions can resolve related entities into one and make connections between distinct entities through interactions and relationships to derive context, and this context gives investigators a far more unified and accurate picture of where true risk lies. Furthermore, advanced analytics at the transaction, entity, and network-level can support the generation of risk-scored alerts, allowing analysts to prioritize and focus their efforts.

 

Unlocking New Opportunities and Insights

When Scott Nathan joined State Street, he was excited to learn that the company was interested in trying something new, as the legacy approach to AML was falling short. “We process and persist data in ways that are unlike any traditional commercial bank, and that presents unique challenges but also really interesting opportunities to use new technology,” said Scott.

State street bank

Scott acknowledges that up until recently, many financial institutions relied on linear models, which targeted many scenarios and specific behaviors, yet lacked the context to identify risk that may look different from that pre-defined set of typical typologies. This resulted in a lack of visibility into activity happening throughout the markets and across the financial services ecosystem.

 

Today, Scott reports that State Street uses AI and machine learning technology to detect, analyze, and visualize markets-related risk. The technology enables the bank to enrich data to create a single entity view and then build networks to understand customer activity, inherent risk, and how its products are potentially being abused. This approach leads to a more streamlined and optimized detection process.

 

A context-led approach empowers State Street to identify risk with fewer false positives, enabling investigators to focus on genuine risk and make more accurate decisions in their investigations. Most importantly, it helps Scott and his colleagues protect both the company and the financial system as a whole from the dynamic threats associated with financial crime.

 

To learn more about contextual monitoring and how State Street has implemented this approach to improve its markets AML processes, watch the full webinar here.

You may be interested in…

Better decisions start here

See how our Contextual Decision Platform transforms every operational decision you make.

Related Solutions