Sigma Synthetic Fraud v4 has been released by Socure, the leading provider of Artificial Intelligence for digital identity verification, fraud prevention, and sanctions screening. The product employs advanced machine learning and a wide range of third-party and network feedback data to uncover patterns associated with pervasive synthetic identity fraud. The Deloitte Centre for Financial Services estimates that synthetic identity fraud will cost at least $23 billion by 2030.
Synthetic identity fraud is a financial crime in which the information of a real person is stolen and combined with other falsified personal information to create a fictitious identity that is then used fraudulently. After opening an account with a synthetic identity, the perpetrator will typically build up a positive credit score, open multiple accounts, and often appear to be good customers while going undetected until they decide to cash out, or “bust out” by using up all available credit lines and disappearing.
Socure detects and stops synthetic fraud during onboarding before the fraudster has a chance to cause havoc in the financial ecosystem. Socure estimates that synthetics account for 1-3% of open accounts at US financial institutions, based on a comprehensive study.
Sigma Synthetic Fraud v4 draws from a variety of “Proof of Life” data sources, such as property records, driver’s licenses, and educational data, adding a new level of accuracy so that organizations can confidently verify younger and immigrant demographics with a small digital footprint. Without these types of proof of life data sources, these segments of the population may be perceived as synthetic fraudsters and excluded from the financial ecosystem.
“Synthetic fraud cannot be detected accurately with rules-based systems or third-party fraud solutions,” said Yigit Yildirim, SVP, of Fraud and Risk Products at Socure. “Socure’s AI engine analyses anomalies to uncover multiplex synthetic-specific features that distinguish legitimate thin-file consumers from synthetic fraudsters with high accuracy in real-time — and without causing friction for good users.”
When criminals combine genuine and falsified information to create new, fictitious identities, they can fraudulently apply for loans, credit, and government benefits, or move illicit funds. As fraudsters’ AI-powered schemes become more sophisticated, distinguishing malicious synthetic behavior from that of good consumers becomes more difficult than ever, making it the fastest-growing form of financial crime in the United States. Synthetic fraud can cost ten times as much as third-party identity fraud per incident. Benefits fraud, P2P fraud scams, and romance swindling all have much higher “profit” per synthetic fraud opportunity.
The threat is exacerbated by the proliferation of “money mules.” Money mules transfer or move illegally obtained funds to make tracing more difficult, frequently using fictitious identities to avoid detection. Money mules were once real people. However, bad actors in transnational organized crime rings that need to launder millions of dollars are now creating synthetic identities to control money mules in order to facilitate the movement of illegal money.
Socure’s multi-layered, best-in-class approach stops synthetic identity fraud by correlating PII, events, and behaviors across businesses and locations using real-time and historical data, velocity intelligence, entity resolution, and link analysis.
The following improvements have been made to Sigma Synthetic Fraud v4:
- Email Risk Enhancements That Are Innovative: Email tumbling, or the practice of creating “alias” email addresses by inserting punctuation marks such as periods between letters, frequently indicates malicious intent. Sigma Synthetic Fraud v4 detects tumbling techniques commonly used in synthetic fraud, allowing customers to identify and block the bad actors behind them.
- Unrivaled Consortium Data and Feedback: Socure can identify multiple identity elements across the consortium and continuously optimize machine learning algorithms to drive the highest accuracy in the market by bringing together a network (Socure Risk Insights Network) of 1,900+ of the world’s largest organizations spanning diverse industries and government agencies. Socure’s database now contains two billion known good and bad identities, thanks to over 150 million rows of outcomes added in the last year.
- Human-in-the-Loop Machine Learning: For unlabeled or mislabeled raw data, Socure fraud investigators provide clean, corrected, and properly classified fraud labels. The labeled data, which is based on actual synthetic incidents and patterns, is used to create training data. As a result, the model is trained to think like a fraudster and uses this intelligence to improve its detection of evolving synthetic threats. This one-of-a-kind machine-human intelligence can be used to detect synthetic identities during onboarding and account changes, as well as to uncover “sleepers” hidden within portfolios.
- Real-time Fraud Attack Detection: Socure’s velocity engine monitors how frequently a person’s personal information is used in applications and how frequently that information is linked to other data across the Socure Risk Insights Network. Large-scale data analysis can aid in the prediction of fraud attacks before they occur.
- Embedded Link Analysis: To track fictitious identities across the Socure Risk Insights Network, link analysis searches tens of thousands of correlations between an entity’s name, address, email address, phone number, SSN, DOB, IP address, and device intelligence. Assume a bad actor creates accounts with different names or Social Security numbers but uses the same email address, phone number, or physical address. Link analysis will quickly identify these linked fraudulent accounts in this case.
Socure’s Sigma Fraud Suite, which includes add-on device intelligence and behavioral analytics, is the industry’s most accurate identity fraud solution, utilizing comprehensive network feedback, velocity intelligence, link analysis, entity resolution, and cutting-edge machine learning to solve a wide range of third-party and synthetic identity fraud.