False positives caused by Volume and Value (V&V) calculations violating a rule or a threshold are a significant cause for concern among anti-money laundering (AML) teams. According to industry estimates, close to 50% of the alerts generated by transaction monitoring systems (TMS) are triggered by a V&V calculation violating a rule or threshold. This is largely because TMS V&V alert thresholds are regularly triggered by individual consumers, which often make up a large percentage of a financial institution’s client base.

While a TMS plays a key role in the fight against financial crime, its capabilities are limited. These systems generate overwhelming numbers of costly false positives that distract the attention of investigators away from cases that most require their attention. Every false positive produced by a TMS, no matter how little risk it carries, should be reviewed. Investigators spend time examining the alert, gathering data, moving between tools/screens, and cobbling together research just to clear a false positive.

To improve the accuracy of V&V predictions, and waste less of your team’s valuable time, models need to consider additional data across a wider spectrum of real-world transaction activity. AML teams can now apply AI-enabled technologies, like the QuantaVerse False Positive Reduction Solution, to determine the nature of V&V-triggered risk and drastically cut the false positive investigations they must handle.

How AI Reduces False Positives Coming from the TMS

To help prevent investigative teams from being inundated by V&V false positives, the QuantaVerse False Positive Reduction Solution works before the TMS tests transaction data. By leveraging AI models that predict volume and value across a wider array of transaction activity profiles, QuantaVerse fine-tunes V&V analysis before the TMS has a chance to create a false positive.

QuantaVerse cuts the number of false positive alerts by classifying the risk of each transacting party, down to the pseudo-client level. By solving both the data problem and the risk segmentation problem, QuantaVerse enables existing TMS rules and models to work as promised. It has been proven to reduce the costs associated with investigating false positives by 20 to 40%.

By augmenting algorithmic content and broadening the number of signals against which it makes predictions, the QuantaVerse Platform provides higher accuracy: one of the metrics that the QuantaVerse AI models examine is distributions of activity over time. This considers the number of transactions and the dollar value of transactions across broad time periods with deep granularity to better determine if current behavior is truly anomalous. Credits, debits, and other transaction types can all be examined and taken into consideration to determine the level and characterization of risk.

One QuantaVerse customer found that V&V was triggering roughly 50% of the alerts coming from their legacy TMS. The QuantaVerse Platform was able to cut V&V-related false positives in half. Effectively, QuantaVerse prevented 25% of TMS alerts from being created. 

Beyond V&V-triggers, the QuantaVerse Platform helps clean up and make sense of other incongruities which may not be good indicators of risk or suspicion. Automatically clarifying jurisdiction or comparing economic purposes helps to further cut false positives and more accurately adjudicate alerts.

Don’t Let False Positives Overwhelm Your Investigative Team

Offered by AML RightSource, the leading outsourced provider of AML, KYC, and Bank Secrecy Act compliance solutions, the QuantaVerse Platform helps companies manage financial crime risks more effectively and affordably using powerful AI, machine learning, and data analytics tools. The QuantaVerse Platform automates all three of the big challenges that AML teams face. QuantaVerse flips the tables on financial crime and the criminals behind it with solutions that are proven to:

  • Reduce false positives that a TMS would otherwise create, reducing the number of investigations that are conducted
  • Automate every step of the investigation process, eliminating the time investigators waste on research and instead letting them focus their invaluable expertise adjudicating cases
  • Identify false negatives using AI that learns patterns and then finds the anomalies that indicate risk which is otherwise being missed.

To learn more, please visit: www.quantaverse.net.