Spotting Fake Employer Scammers Before They Attack

Fake Employer

Point Predictive’s Chief Fraud Strategist Frank McKenna recently penned a commentary piece for Auto Remarketing, a periodical covering the pre-owned auto industry. In it, he discusses the rise of shell companies and fake employer scams and how Point Predictive’s approach can combat them.

Fake employers have become an increasingly vexing problem for financial institutions and other lenders, Frank writes. While some “fake employers” are legitimate companies who become unwitting accomplices in a fraudster’s scheme, others are complete fabrications. Unscrupulous scammers invent these employers, sometimes with bits of real-world information, to appear more trustworthy on applications for auto loans or other products. Sometimes, the goal is to secure better financing terms; in other cases, the borrowers have no intention of repaying the debt. In any case, engaging in this fake employer fraud results in an average charge-off rate of 40%.

Frank explains how Point Predictive has combined Artificial Intelligence and Natural Intelligence (Ai + Ni) to identify 11,000 fake employers and counting, accounting for more than $2 billion in suspicious activity in the past two years. He outlines a five-step detection process.

5 Steps to Detect Fake Employer Fraud

Point Predictive’s fraud analysts follow a rigorous five-step process to identify and expose fake employers involved in fraudulent auto loan applications.

Step 1: Proprietary data matching and AI scoring
The initial step involves real-time evaluation of 2 million to 3 million applications monthly against 26 billion proprietary data points. Point Predictive assigns a risk score to each application, accompanied by up to 140 red flags for further investigation.

Step 2: Analysis of alerts and specific concentrations of fraud
With the help of “fraud bots,” investigators work to identify unusual patterns and clusters in employer data. The process includes scrutinizing increased application volumes from a single employer, repeated phone numbers, and patterns of inflated income, among others.

Step 3: Evaluation of known frauds and validated incomes
Fraud analysts then examine whether the identified employers are associated with known frauds and fraudulent paystubs, distinguishing genuine employers from those with suspicious activities.

Step 4: Examination of public records
Investigators review Publicly available information and search for red flags such as unregistered or non-licensed businesses, hastily assembled websites, and inconsistent business activities.

Step 5: Identification of likely fake employers
After a comprehensive analysis, the fraud analyst determines whether the business is legitimate or a potential fake. Once flagged as potentially fake, lenders can subject the application to further scrutiny.

Some Closing Thoughts on Fraud Prevention

The Ai + Ni collaboration provides the best defense against the rising tide of fake employer scams, Frank concludes. He also offers some tips for financial institutions looking to stay ahead of the fraudsters:

  • Leverage consortium red flag solutions for early detection.
  • Establish an internal negative file to check employer names and phone numbers.
  • Flag any application from an employer associated with two or more fake paystubs for manual review.

To read the full article on Auto Remarketing, click here, or contact us to learn about how Point Predictive products like BorrowerCheck and IncomePass use Ai + Ni to detect fake employer fraud.

Talk to Us