Sure Profile™

Synthetic identity fraud is a type of fraud in which a criminal combines real and fake identity elements to establish a credit record under a new identity. Fraudsters often use Social Security numbers from children, the elderly and others combined with additional personally identifiable information data elements to apply for credit. The fraudster then uses this information to open fraudulent accounts, which often max out credit lines before busting out.  

Synthetic identity fraud allows the criminal to steal money from creditors who extend credit based on the fake identity.  

Sure Profile Risk score and Attributes. For inquiries that pose a synthetic identity risk, Experian provides a risk score predicting the likelihood of synthetic identity fraud. The score allows you to adjust step-up authentication and/or secondary review levels to target the riskiest applicants. Approve more new customers by applying the proper verification strategies necessary to validate the consumer’s true identity. The Sure Profile Score’s underlying attributes are available to customers that prefer to build and maintain internal strategies and models to combat Synthetic ID.

• Initial protection at acquisition 
• Reduction in operational costs and resources to downstream verification processes   
• Upfront insight into synthetic identity fraud risk to continually monitor approved trades   
• Reduction in collections-related operations   

Sure Profile works in concert with additional fraud tools, such as CrossCore^® and Precise ID^®, to provide insight into synthetic identity risk as part of a multilayered fraud strategy. For example, identities flagged as high risk by Sure Profile can be processed by eCBSV, offered by Experian. Alternatively, they can be sent to CrossCore^® Doc Capture for document verification and facial comparison. 

Experian’s machine learning models analyze various trade and identity behaviors to isolate traits and predict synthetic identities. By uncovering certain trends and anomalous instances, our machine learning models continue to improve synthetic identity-capturing capabilities.