Powered by machine learning to help better proactively detect fraud, financial institutions can monitor suspicious non-monetary activities for individuals to complement rules-based approaches and detect fraudulent activities.
GRID Active Fraud Detection has added a User Behavior Analytics (UBA) model, powered by machine learning, to help better proactively detect fraud. By tracking individual user data and activities to identify suspicious deviations from the user’s normal behavior, financial institutions can monitor suspicious non-monetary activities for individuals to complement rules-based approaches and detect fraudulent activities. With this enhancement, customers will see an alert within GRID Active based on their defined risk factors.
A sample of the risk factors are defined as follows:
Unusual Login Time of Day
Changed Password/email address/phone number.
The machine learning model is used for tracking, collecting, and assessing individual user data and activities to find fraud that might be detectable by changes to an individual user’s behavior. If the model detects a change from what has been seen before across any of these parameters, a risk score will be generated, and if the cumulative score is over a configurable threshold, GRID Active triggers an alert.
WHY DEFENSESTORM FRAUD DETECTION
Built for Banking, GRID Active Fraud Detection provides continuous monitoring and alerts from data across the network, online banking platform, and core to proactively detect and stay ahead of evolving fraud threats and stop cyber fraud before funds leave the organization. Integrating Information Security and Fraud departments in a single platform, we defend against threats, including fraudulent account opening/loan applications, account takeovers, payment fraud, money laundering, and internal fraud.
DefenseStorm is committed to providing solutions that stay ahead of the ever-changing threat landscape. We continually innovate and update our technologies to ensure that our clients receive the best possible protection against both known and emerging threats.