Data Consortium

Benefit from Data Covering More Than 232 Million Loan Applications
Consortium members benefit from data on more than 232 million lending applications representing more than 90 million unique applicants and growing across auto, mortgage and personal lending. For each application, the consortium has data including:
  • Over 29.6 Billion unique data points
  • Over $13 Billion in Early Defaults
  • Over $2.9 Billion in Confirmed Fraud
  • Over 156.8 million unique income reports
  • Over 17 Million Unique Employers Across the US
  • More than 11,000 Fake employers
  • Over 110,000 Car Dealerships
  • Home phones, Cell Phones, Employer Phones
  • Address and Location Data
  • Risky social security numbers (SSNs)
  • SSNs linked to default or prior fraud
  • VINs and Collateral linked to default or prior auto loan fraud
This powerful data is used to build artificial intelligence (AI)-powered scoring models that help lenders automate the lending process – increasing loan pull-through, reducing origination cost, and improving the borrower experience – and reduce fraud and early payment default (EPD) risk

10 Ways The Consortium Helps You Identify Fraud

Identify Fraud Risk of Potentially Fake Employer Information
Fraud risk is present if the borrower or dealer uses a fictitious employer that has been detected at other lenders. Point Predictive identifies on average 100 new fake employers a week and has identified more than 11,089 fake employers as of July 2024. According to Point Predictive’s analysis of loan performance, 40% of loans funded with a fake employer will charge off.

Fraud Risk is Present If Your Applicant Recently Reported Being Employed by a Gig Employer, But Switched

Find out if the applicant is “gig hiding”. The term “gig hiding” refers to a suspicious change in employer within 30 days of an application from a gig industry employer to an employer in another industry. Specifically, Point Predictive tracks incidences when a consumer uses a gig employer (Uber, Lyft, Door Dash, Uber Eats, etc.) for an auto loan and submits another application within 30 days, stating an employer that does not fit the “gig industry” category.

In 2023, we saw “gig hiding” hit over 8%, indicating that subsequent applications submitted by gig workers after the initial application could contain employer misrepresentation. Early payment default is also 2.5 times the average rate of default when gig hiding is present on the application.

Identify Straw Borrowers
Find out if the borrower is likely purchasing the vehicle for someone else. We can identify recent applications for the same borrower, which may have had a previous co-borrower removed.

Identify If The Vehicle Price Increased Dramatically Recently
Find out if the vehicle being purchased is priced accordingly or if the dealer is attempting to “powerbook” the loan. Price inflation can present a significant risk to the relationship between the lender and the dealership. For instance, in 2020, roughly 20% of applications had a vehicle priced at least $1,000 higher than advertised.

Identify If Other Lenders Find The Dealer Risky
Find out if other lenders recently terminated the dealership or if it has high rates of fraud and default. Our proprietary data repository can identify dealership risk across lenders, so you don’t have to fight fraud alone.

Identify If The Vehicle Make and Model Is Targeted by Fraudsters
Vehicle makes and models come with differing levels of risk. Whether these makes and models are popular because of reliability, cost to own, or just that they are popular among fraudsters, you can gain an understanding of collateral risk patterns and fraud-ring risk. Learn more in our 2024 Auto Lending Fraud Report.

Spot Borrowers Who Recently Changed Their Income Significantly
Ever wondered if an applicant inflated their income on an application?  If a customer doesn’t qualify for the loan they want, they may try again with some adjusted numbers.  Point Predictive collects and tracks income discrepancies in applications across lenders to prevent income misrepresentation. A 2019 study in Canada by Equifax showed that 19% of surveyed millennials had not been entirely truthful on a credit or loan application.

Identify Borrowers Who Changed Their Employer Recently
Similar to income discrepancies, applicants may choose to show a different employer.  This commonly occurs for self-employed borrowers who may find better luck listing the company name rather than self-employed when applying for loans.

Identify Potential Credit Washers
Coached by credit repair schemes, some borrowers will either create synthetic identities by using alternative identifiers or wash their credit.  Only Point Predictive offers a credit washing detection capability. By looking for sudden swings in credit scores with a sudden drop in negative tradelines over a short time period.

Leverage More than 29 Billion Unique Data Points Not Available On Bureau or Public Record Source

We leverage data and science to help lenders utilize their data in combination with Point Predictive’s proprietary risk data repository. This unique approach allows us to mine historical patterns and build AI-based solutions that make the lender’s underwriting process smarter and more efficient, while reducing the risk of fraud and early payment default.