1 in 5 loan applications have inflated income and 1 in 12 pay stubs are bogus


SAN DIEGO – () –PointPredictive Inc., the San Diego-based company that develops artificial and natural intelligence [Ai+Ni] models using machine learning, found that one in five loan applications have significantly inflated income.

In a study of over three million claims, PointPredictive compared the claim’s reported income to the borrower’s actual income and found that on average, 20% of reported income was significantly inflated by 15% or more. In the same analysis, the income applicants report to one lender can differ significantly from what they report to another within short time frames. In fact, among applicants who applied to multiple lenders, 1 in 10 changed their income by more than 50% from what they reported to the original lender.

“While the risk of false loan tax returns is high, the approach lenders use to identify it and prevent it from happening is often counterproductive,” says Frank McKenna, chief strategist of the fraud at PointPredictive. “Some lenders ask for pay stubs on up to 100% of approved claims, but what they receive includes countless bogus documents forged or generated on the Internet. Our research indicates that one in 12 payslips a lender receives in response to a request for proof of income is fake or tampered with in some way. Asking for pay stubs as “proof” to validate income is a broken paradigm – every claimant or fraudster who needs to do so has already found the workaround. As a result, lender risk management departments are inundated with so many pay stubs that the quick scans needed to track volume often miss forged or bogus documents. Additionally, consumers will sometimes abandon loan processes when lenders request this documentation as it places an undue burden on the consumer to prove their information. ”

As part of the analysis, PointPredictive engaged its team of fraud analysts to investigate the problem of fake payslips. Analysts have identified over 300 websites offering to generate bogus payslips typically costing between $ 5 and $ 15. The average time it took for fraud analysts to create a realistic fake pay stub on one of these sites was four minutes. The prevalence of bogus pay stub sites means that asking for pay stubs as proof of income has become noticeably unreliable.

“Changing the way we think about revenue validation is critical to the future of lending,” says Tim Grace, CEO of PointPredictive. “Gone are the days when applicants had to provide pay stubs to get a loan. Sixty percent of employees have direct deposit and never even receive a paper pay stub; asking the applicant for it really disrupts the loan process. Asking consumers to produce a paycheck stub often requires them to go to their employer and figure out how to obtain such a document. When asked, many employees never even see what their pay stub looks like or don’t know how to get a copy. This is the kind of barrier that will cause many borrowers today to look elsewhere for loans or credit cards. We believe a better way is to take advantage of technology to accurately assess the reasonableness of income BEFORE requesting onerous documentation. we launched IncomePass™ last year to fundamentally change the way revenue is posted.

IncomePASS analyzes a borrower’s reported income against millions of reported income and salaries from seven diverse sources. Then, using the applicant’s employer, occupation, job title, residence, and estimated years of experience, a sophisticated machine learning model predicts whether borrowers’ reported income is within the range.

Real-world validation of the solution by the lender shows that the approach works. Lender test results show that, on average, income reported on 75% of applications can be approved and approved at an accuracy rate greater than 90%. For lenders who request pay stubs on 100% of their loans, they can now choose to selectively target the subset of loans whose income is unreasonable or likely to be inflated to confirm whether income and documentation are valid. Alternatively, for lenders who wish to be able to validate 100% of their reported income, they can use IncomePass to validate them all before funding.

IncomePASS is available for banks, lenders, and card issuers to validate income reported on apps. The service is available today for real-time integration into loan and underwriting workflows.

For more information on PointPredictive’s IncomePass, please contact [email protected]

About PointPredictive Inc.

PointPredictive Inc. Enables Lenders to Fund More Loans Simply Through a Unique Combination of Artificial Intelligence and Natural Intelligence [Ai+Ni] to power machine learning technology solutions. PointPredictive helps auto, mortgage, retail and personal loan finance companies identify consumer applications with truthful, reliable information without the intense querying and data verification caused by less technological solutions currently in use. With a legacy of being the most trusted fraud and misrepresentation analysis solution providers, PointPredictive has transformed that trust to make it easier for lenders to fund more loans to more consumers. PointPredictive uses powerfully orchestrated big data from millions of examples of true and fake loan applications, billions of derived proprietary data elements, and scientifically-selected third-party data sources to create powerful machine learning models with the natural intelligence added to human experience. Located in San Diego, CA, you can find more information about PointPredictive at www.pointpredictive.com.


Comments are closed.