DataVisor Automated Rules Engine Eliminates the Headache of Manual Rule Tuning for Fraud & AML Teams

April 02 13:00 2017 Print This Article

MOUNTAIN VIEW, Calif., April 03, 2017 (GLOBE NEWSWIRE) — DataVisor today announced the latest addition to its full stack analytics platform, the DataVisor Automated Rules Engine, a rules engine that maintains itself. The patent-pending technology generates rules automatically, on a daily basis, based on attributes detected and provided by the Unsupervised Machine Learning (UML) Engine. The rules within the Automated Rules Engine are continuously tuned to ensure that they’re still highly effective and accurate, reducing manual review time and enabling risk teams to more easily maintain rule effectiveness.

Rules engines are a key part to many companies’ online fraud detection and anti-money laundering infrastructures. As online criminals constantly change and adapt their attack techniques, it becomes nearly impossible to add and modify the hundreds or thousands of rules within the rules engine to detect them. Unsupervised machine learning catches evolving attacks by correlating user and event attributes of coordinated attack campaigns without rules or labels. The Automated Rules Engine then uses the results of the UML Engine to create human-readable rules around them, automatically adapting to these evolving attacks.

With a DataVisor Automated Rules Engine, a company can:

  • Create rules automatically – The DataVisor Automated Rules Engine generate new rules and retires decaying rules based on DataVisor’s UML results.
  • Monitor effectiveness of its rules – The dashboard provides performance details of a rule such as how many users the rule detected, as well as the accuracy of a rule over time, so they can be applied or retired as necessary.
  • Create manual rules – The users can create custom rules using their valuable domain expertise with both Boolean logic and complex operands.
  • Backtest rules – The DataVisor Automated Rules Engine can also backtest manually-created rules against historical data before deploying them on the system in order to reduce risk of deploying poorly designed rules.

“While rules certainly have their place within the detection ecosystem,  they can be difficult to maintain and aren’t always reliable. Online criminals are quick to change their attack techniques and patterns, and rules quickly become obsolete, placing a huge burden on internal fraud and AML teams to update and tune them constantly,” said Yinglian Xie, CEO and co-founder, DataVisor. “The DataVisor Automated Rules Engine brings a new level of innovation to rules. It not only saves time on creating, testing and deprecating rules, but makes them stronger and more accurate by strengthening them with Unsupervised Machine Learning. It’s a new and strong weapon for our customers to use in the fight against online crime.”

If you’re interested in learning more about the DataVisor Automated Rules Engine, please visit: https://www.datavisor.com/platform/automated-rules-engine/

About DataVisor
DataVisor is the leading fraud and financial crime detection service utilizing unsupervised machine learning to identify attack campaigns before they conduct any damage. DataVisor protects some of the largest organizations in the world from attacks such as account takeovers, fake account creation, money laundering, fake social posts, fraudulent transactions and more. For more information, visit www.datavisor.com.

CONTACT: Contact

Lisa Mokaba
Head of Media Relations
DataVisor
[email protected]
  Categories:
view more articles

About Article Author

Jonathan Yaniv
Jonathan Yaniv

Jonathan is the founder and editor-in-chief of TrustedNerd.com. Covering major tech shows such as CES, Jonathan is always there for the latest tech news. Want your gadget to be reviewed or have a release you'd like to be considered for publishing? Send Jonathan an email, jonathan [at] trustednerd.com

View More Articles