arrow left facebook twitter linkedin medium menu play circle
March 24, 2021 - Claire Zhou

6 Common Characteristics of Synthetic Fraud

Synthetic fraud is a growing challenge, costing U.S. lenders about $6 billion a year in bad debt and accounting for 20% in credit losses. This type of fraud occurs when criminals combine real customer data with fake details to form new identities. Because some of these details are valid, it’s hard for traditional fraud detection measures to detect synthetic fraud until after financial losses are incurred. 

These losses are nearly impossible to recover. Without knowing which details were real and which ones weren’t, debt collectors are often unable to pursue the fraudsters. 

However, financial institutions can improve their efforts to detect synthetic fraud by identifying several common characteristics.

1. Repeated Use of the Same Social Security Number

Repeated use of the same SSN is a potential indicator of synthetic identity fraud. Every SSN is unique, so there’s no reason for the same SSN to be used by multiple people. 

2. Accounts Created Using the Same IP Address

IP addresses are like the SSNs of devices. When multiple accounts are created by the same IP address, it could be the work of one person (or bots) trying to emulate multiple people.

3. Same Personal Details Being Used to Create Accounts

One of the hallmarks of synthetic fraud is to combine authentic information with fake details. For example, a scammer might use a real address and phone number with a fake name. 

Authentic personal data is becoming easier to come by. Experian reports that a Social Security number can be obtained on the dark web for as little as $1, while full packages containing a name, birthday, SSN, and other details go for just $30. This low cost of access makes it easier to create multiple synthetic identities at scale and serves up plenty of challenges for fraud prevention teams.

4. Credit File Depth Doesn’t Align with Customer Profile

Comparing a customer’s credit profile can reveal potential synthetic identities. Fraudsters typically build their credit profiles quickly by making small purchases and paying them off. But an authentic customer’s credit profile may be much deeper with a longer credit history.

5. Addresses are Near Large Airports or Shipping Destinations

A white paper published by the U. S. Federal Reserve mentions that many synthetic identities use addresses that are near large international airports or shipping centers. This makes it easy for fraudsters to collect goods and disappear before they get caught.

6. Multiple Authorized Users on the Same Account

It’s a red flag when an account has multiple authorized users (especially those that don’t appear to be related to each other). This could indicate a sophisticated crime ring with multiple participants.

How DataVisor’s Fraud Detection Platform Improves Synthetic Fraud Prevention

The Federal Reserve notes that focusing on just one of these factors could result in a high false-positive rate. It also puts legitimate customers at a disadvantage and could impact your reputation. 

To overcome these and other risks, it’s important to take a comprehensive approach that includes multiple methods of fraud detection and prevention. A multi-layered fraud detection platform boosts synthetic fraud detection, making it much more difficult for fraudsters to wriggle through defenses. Holistic data analysis provides a high level of accuracy, and a comprehensive fraud platform that uses multiple layers of protection also enhances operational efficiency. 

DataVisor’s comprehensive fraud detection platform takes a multi-layered approach to fraud prevention and detection that includes machine learning, an advanced rules engine, knowledge graph, and real-time analytic capabilities that enable rapid detection and response for your fraud team. To learn more about DataVisor’s fraud detection approach, download A Guide to Fight Synthetic Fraud with a Multi-Layered Detection Platform today.

Photo of Claire Zhou
about Claire Zhou
Claire is a Senior Product Marketing Manager at DataVisor with over 5 years of marketing experience in security and fin-tech. She is passionate about empowering enterprise customers with AI-based solutions. Her expertise spans data analytics, cybersecurity, and fraud prevention. Claire has an MBA from UCLA.
Photo of Claire Zhou
about Claire Zhou
Claire is a Senior Product Marketing Manager at DataVisor with over 5 years of marketing experience in security and fin-tech. She is passionate about empowering enterprise customers with AI-based solutions. Her expertise spans data analytics, cybersecurity, and fraud prevention. Claire has an MBA from UCLA.