Unsupervised Machine Learning Engine analyzes the hidden connections between fraudulent applications to detect suspicious applications even if each application in isolation is not suspicious. This allows DataVisor to stop application fraud in real time, without training data or labels, stopping the fraudster at account approval.
Stop Sophisticated Attack Techniques
Fraudsters utilize proxies, VPNs, or cloud-hosting services to hide their tracks from IP blacklists and rules-based systems.
Armies of Free Emails
Fraudsters use popular free email services to mass register realistic-looking accounts to use for their own attacks or to sell to other fraudsters.
Attackers use sophisticated scripts to carry out large scale attacks, appearing as though the sessions are from many distinct users.
Why UML is Needed to Stop Application Fraud
The wide availability of personally identifiable information allows fraudsters to apply for accounts using stolen or synthetic identities. Synthetic identity theft, where fraudsters create an entirely new fake identity, is almost a perfect crime as there is no consumer victim to complain about the fraud. Coupled with sophisticated mass registration techniques, these synthetic accounts appear legitimate and remain under the radar when reviewed in isolation. DataVisor’s Unsupervised Machine Learning Engine analyzes all accounts simultaneously, allowing it to detect the hidden connections between fraudulent accounts, even if each account is not suspicious in isolation.
Accuracy and Coverage
By detecting entire crime rings at once, UML is able to achieve unrivaled detection accuracy and coverage at the same time.
Detect Unknown Threats
UML uncovers the hidden connections between accounts without training data or labels, allowing it to detect changing and entirely new attack patterns.
Improve Customer Experience
UML’s accuracy allows companies to identify good customers and reduce authentication steps, streamlining customer experience.
Learn How DataVisor Fights Application Fraud
What’s Happening with Application Fraud
Synthetic identity theft – when a fraudster creates a composite identity from a mix of real and fake information and applies for loans with the identity – is a growing problem for financial institutions.
Online digital lenders have proliferated in the last few years, and traditional lenders have also rebalanced their focus and have increased their digital efforts across all products trying to catch up with their nimbler rivals. As a result, the potential target for fraudsters to attack has become significantly larger and more lucrative and they haven’t held back their efforts to inflict maximum financial damage.
Wells, wells, wells, what do we have here? Last week the news broke that Wells Fargo had “been hit with $185 million in civil penalties for secretly opening millions of unauthorized deposit and credit card accounts