Today’s fraud tools are typically designed to focus on real-time prevention at the customer access point. Limiting fraud detection to look at real-time events can miss a bigger picture of fraud. Knowing whether a caller can be trusted is critical, but what about the account they are trying to access? Has that account been accessed by 10 other people on the same day? A caller on the phone might sound innocent, but, what if you knew the account they are calling about had already been accessed through the IVR 80 times in a single day? Could knowing that change your approach to fraud prevention?
Just like regular customers, fraudsters also use the IVR for seemingly innocuous activities like checking account balances. But with fraudsters, this simple activity could hint at an attempted account takeover. Using these interactions, along with machine learning, can provide insights on which accounts might be under fraudster surveillance.
How Pindrop Is Helping Contact Centers Monitor Account Risk
Pindrop® Protect can help monitor accounts to provide intelligence on the “who” or which account is at-risk from fraudster attack. This second vector analyzes which accounts fraudsters are targeting and provide a score based on the likelihood of fraudulent activity we call account risk. We use signals from the IVR to help provide insights on which accounts fraudsters may be already targeting and the system can integrate data from around the organization to enhance the score’s accuracy.
Monitoring an account for risk means that if a fraudster bypasses existing controls, monitoring the account he was attempting to breach can act as a failsafe. Measuring account risk using Pindrop technology can provide a fraud team whose accounts are being surveilled by fraud rings in some cases 60 days in advance of an account takeover attempt.
Today, Protect customers can use call risk scores in real-time to make determinations about the risk the caller might present. By adding account scores that get updated over time, artificial intelligence assesses possible connections to previous fraudulent attempts, as well as cross-channel account activity patterns.