The following post is part of a series of blogs written by MeridianLink® Partners who will be attending MeridianLink LIVE! To learn more about AI in lending and the event, click here.
Here’s the reality that most lenders miss – approximately 90% of borrowers are truthful when they fill out an application. Yet the traditional lending process subjects everyone to the same rigorous interrogation because of the 10% who aren’t.
This paradox has resulted in false positives and manual reviews that have grown to unsustainable levels for companies trying to grow. Traditional red flags can have false positives of 1000 to 1, causing underwriters to miss fraud caused by decision fatigue because of having to review hundreds of false positives.
Ironically, these processes can also create fraud. As companies have increased their requests for paystubs, the rate of forged paystubs has grown. In a survey conducted by Point Predictive, some lenders reported that as many as 1 in 5 paystubs they receive are forged.
The Power of Proprietary Risk Data Holds the Key
Our massive proprietary risk data repository differentiates Point Predictive’s approach. We’ve captured 80 billion risk insights from over 256 million historical applications, 300 million reported incomes, and 93 million unique identities submitted—data that the credit bureaus do not have access to.
This data provides insights, supercharging fraud programs and allowing credit unions and other lenders to automate up to 70% of all their fraud decisions instantly.
The information powers solutions like IEValidate™, which verifies a borrower’s income and employment with just a single piece of information—no paystubs, no employer calls, and no friction.
Credit unions are improving the member experience by removing that friction, which in turn is increasing their conversion rates.
In one case, a lender began using our income and employment solution to waive paystub requirements on low fraud risk loans. As a result, the capture rate on that population tripled (jumping from 13% to 40%). On average, lenders that remove the friction of a paystub, see their conversion rates double on low-risk loans.
Uncovering Hidden Fraud Patterns From Billions of Data Points
You need technology to analyze billions of data points on historical applications to find fraud that is slipping through on current applications. Many credit unions are unaware that income and employment fraud makes up around 50% of fraud perpetrated, according to our data. This type of first party fraud is typically very difficult to spot.
Our data is helping the industry identify fraud patterns that traditional systems simply can’t detect. We’ve identified over 14,000 fake employers being used in employment fraud schemes targeting hundreds of lenders, banks, and credit unions across the US.
And it doesn’t stop at income and employment fraud. Point Predictive has used this data to identify clusters of frequent perpetrators of synthetic identity—people who combine real and fake information to fabricate a completely new identity.
Synthetic identity fraud has also increased by 500% since 2017. Point Predictive’s data and fraud analyst teams have identified over 11,000 frequent synthetic identity fraudsters and actively alert our customers in real-time if one of those identities is used for a loan at their organization.
The Double Win: Less Fraud, More Automation
This approach’s most powerful aspect is that it simultaneously delivers two seemingly contradictory benefits: better fraud detection alongside higher automation rates transforms lending operations.
It is transforming the way forward-thinking companies improve the member experience. Neighbors Federal Credit Union, Affinity Federal Credit Union, Heartland Credit Union, and hundreds of other credit unions via our partner integrations, are discovering firsthand that the approach works. They are using Point Predictive to uncover previously hidden fraud while unlocking significant benefits in automating loans for low-risk members.
The Future of Fraud Protection – Applying Friction as Last Resort
The lending industry stands at a critical inflection point. Those clinging to lengthy, document-centric verification processes will continue losing business to competitors offering frictionless experiences.
Smart lenders are adopting what we call a “cascade approach”—using proprietary data and AI as the first verification step and only escalating to more intrusive methods when necessary. In this new paradigm, the question isn’t whether to use AI and proprietary data—it’s how quickly you can implement it before your competitors do.
Learn more at PointPredictive.com
Point Predictive powers a new level of lending confidence and speed through artificial intelligence, powerful data insight from our proprietary data repository, and decades of risk management expertise. The company’s data and technology solutions quickly and accurately identify truthful and untruthful disclosures on loan applications. As a result, lenders can fund the majority of loans without requiring onerous documentation, such as pay stubs, utility bills, or bank statements, improving funding rates while reducing early payment default losses. Subsequently, borrowers get loans faster, and lenders realize a more profitable bottom line.
