Lies, lies, lies.  That is always the case with fraud.   And PointPredictive, the company I work for, just released analysis that finds that mortgage and auto fraud lies follow very similar risk patterns.

Scoring Applications with Fraud Models Detected High Levels of Early Pay Default (EPD)

The study found that by scoring auto loan applications with models built to detect fraud, lenders could detect 50 percent or more of their early payment default (EPD) prior to funding than if they relied on traditional credit scores alone.

When we ran fraud pattern recognition models on the application information provided on EPD loans, we found strong evidence of fraud. This is the same type of behavior mortgage lenders discovered prior to the mortgage crisis when it was determined that up to 70 percent of mortgage EPD was fraud related. The study confirms that using credit scores alone cannot detect fraud or risk of default. Tim Grace CEO PointPredictive

The study encompassed data from millions of auto loan applications submitted by dealers all over the US across all vehicle types. PointPredictive auto fraud models analyzed each loan application and gave it a fraud score. While built to detect fraud, scientists were surprised to find that it did extraordinarily well in the detection of early payment default, a term lenders use to indicate when loans default within the first six months.

The PointPredictive analysis proved that fraud scoring could:

• Detect 14 times more fraud for lenders than current solutions while flagging less than five percent of the total applications.
• Prevent 50 percent or more of a lender’s early payment default losses by identifying those applications that had misrepresentations that would lead to loss.
• Identify risky auto dealers that submit multiple fraud loans up to three months sooner and reduce losses due by 70 percent due to early detection of bad players.

It is Not Surprising Since Hidden Fraud Almost Always Ends Up in EPD

BasePoint Analytics wrote about this same problem back in 2007 when they published a whitepaper on the fact that 30% to 70% of early payment defaults had serious misrepresentations on the initial application.

The study confirmed that misrepresentations grossly affect the risk of a loan, finding that loans containing fraudulent misrepresentations were up to five times more likely to default in the first six months than loans that did not.

BasePoint found that the percentage of EPD loans that can be attributed to a fraudulent misrepresentation on the original application varies between thirty percent and seventy percent. The ratio varies based on a number of factors, including portfolio type, loan program, underwriting policies, and EDP definitions and measurement periods. The earlier the serious delinquency occurs, the more likely it is linked to a significant misrepresentation on the original loan application.

As Auto Loan Defaults Increase, The Problem Could Get Worse

Auto Loan defaults are on the rise.  National Publications like USA Today are reporting loan defaults are 17% higher this year than last.

The eroding loan quality and falling car prices follow a similar pattern that the mortgage industry saw in 2007, prior to the fall of the mortgage market and eventual collapse.

As these loan defaults increase the problem of fraud will be magnified and we will start to see more scrutiny on lending fraud.