BasePoint Analytics

This message contains graphics. If you do not see the graphics, click here to view.



	Fighting Fraud with Frank July 12, 2007 Credit Bureau Reports Hold Insight into Fraud Risk

"...lenders who adopt fraud scores achieve greater profitability than those who continue to use traditional data validation methods..."

Welcome to the second edition of “Fighting Fraud with Frank.” I received great feedback on our first topic of how investment banks can reduce fraud – thank you for the opportunity to again share my thoughts with you on how to combat mortgage fraud risk. This month, I’m writing about how lenders, investment banks and due diligence firms can better leverage credit bureau data, beyond credit scores, to more accurately identify fraud risk early in the loan origination, due diligence or purchase process. This topic was prompted by issues we are seeing repeatedly during the due diligence process. These include the growing trend of people renting good credit histories to rebuild their bad credit, sometimes called piggybacking, as well as services that pay down borrowers’ outstanding balances temporarily to boost credit scores. These trends provide an opportunity to reevaluate the value of credit reports and how they, coupled with predictive analytics, can help identify a borrower’s true risk. Using Credit Bureau Data to Identify Five Types of Mortgage Fraud Credit reports are one of the most under-utilized tools in curbing mortgage fraud. While the credit score is usually a good baseline for determining ability to repay, if used properly, and in conjunction with a fraud score, the credit report also provides important potential fraud indicators. This data can be incorporated into analytic solutions and used to investigate applications and loans that receive high fraud scores. Here are five examples of fraud types that can be uncovered by leveraging the full value of the credit report: Piggybacking - Piggybacking is one of the hottest topics in mortgage news today. To identify piggybacking on a credit report, compare the ratio of tradelines that have authorized users to the total number of accounts to see if a credit score is artificially inflated. An example that shows possible piggybacking is if 50% or more of the tradelines are authorized user accounts and were recently added to the file. Straw Borrower - Someone whose good credit is knowingly or unknowingly used to apply for a mortgage for someone else, typically with bad credit, is considered a straw borrower or straw buyer. A typical straw borrower has few credit lines, but they are in good standing. If there are only a few tradelines on the credit report and the borrower is purchasing a very expensive home, sometimes in an area in which he or she doesn’t live, that application or loan should be investigated further. Identity theft - Many indicators for identity theft can be discovered by cross referencing a mortgage application against information from the credit bureau such as age, social security number and addresses. Another warning is if a credit report shows a significant increase of credit accounts opened within a recent six to nine month period. Income fraud – You can often identify indicators of income fraud using credit bureau data. For example, if a person claims to make $300,000 a year but has no prior car loans or home loans and only has one or two credit card tradelines, this is a red flag. This credit profile is inconsistent with the typical credit history of a person earning a high income, and should be investigated further. Undisclosed assets – This type of fraud is attempted by borrowers intent on getting a better interest rate on the purchase of an investment property. The existing primary residence is not being sold and the existing home loan is not disclosed, causing the debt-to–income ratio for the new mortgage to appear artificially low. To identify this type of fraud, compare the application information to the credit bureau report looking for inconsistencies such as undisclosed mortgages or property tax liens. When lenders review credit reports for discrepancies, it is often a manual process with underwriters whose experience levels may vary widely. It can take an underwriter 30 minutes to pore through an application and consider hundreds of different variables. Multiply this by thousands of applications and it’s no wonder fraud continues to find its way through. The Need for a Fraud Score There is a missing link between relying solely on a credit score to determine risk and what you really need to truly understand the risk of fraud. That’s why there is a need for a fraud score, which is calculated using predictive analytics technology. The fraud score identifies specific high risk applications or loans that should be reviewed further while delivering very low false positive rates. A fraud score works because it includes additional elements to the risk assessment that go beyond traditional credit scoring methods. A fraud score can incorporate other elements of risk such as income, employment, broker information, property information and loan program type to assess the overall fraud risk associated with an application or loan. When the underlying information supplied by brokers, borrowers and appraisers is not representative of the truth, it affects the way a loan will perform over the long term. Technologies that accurately predict the likelihood that a loan contains misrepresentation, and will not perform, are the best solutions for mortgage fraud available today. They augment the FICO score, giving a more accurate characterization of the borrower and loan risk. The need to better predict fraud risk continues to be a key success factor for lenders and investment banks alike. In my experience, lenders who adopt fraud scores achieve greater profitability than those who continue to use traditional data validation methods and manual processes. Predictive analytics technology enables a lender to select the small sub-set of loans (typically 10-15%) that require a more thorough review and allows the lender to quickly fund the vast majority of loans. What’s your opinion? I invite you to share your experiences and comments with me. Your privacy is important to us. If you no longer wish to receive email from BasePoint Analytics, please click here to be removed from our mailing list. If you would like to be added to our mailing list, please click here.


	Frank McKenna, Co-founder and Chief Fraud Strategist of BasePoint Analytics Frank helped develop and introduce advanced predictive technology to detect mortgage fraud. Frank’s vast experience in fraud management has enabled him to identify unique and effective tools to manage lender risk through pattern analysis and evaluating other parties in the transaction, such as mortgage brokers.
	Additional Information Ask Frank Send your questions, comments, and/or ideas for future discussion topics to Frank. The Facts on Fraud Broker Magazine