News Column

Patent Issued for Strategic Loan Default Scoring

June 25, 2014



By a News Reporter-Staff News Editor at Journal of Engineering -- From Alexandria, Virginia, VerticalNews journalists report that a patent by the inventors Dornhelm, Ethan (New York City, NY); Gao, Lu (American Canyon, CA); Gaskin, Joanne (Canton, MN); Wei, Yan (Alameda, CA); Backes, Tracy (Reno, NV); Leverentz, Andrew (San Francisco, CA), filed on February 17, 2012, was published online on June 10, 2014.

The patent's assignee for patent number 8751378 is Fair Isaac Corporation (San Jose, CA).

News editors obtained the following quote from the background information supplied by the inventors: "A strategic default is the decision by a borrower to stop making payments on a debt despite having the financial ability to make the payments. Strategic default is particularly associated with residential and commercial mortgages, in which case it usually occurs after a substantial drop in the price of the corresponding house such that the debt owed is (considerably) greater than the value of the property. Some studies have shown that strategic default risks exceed credit card default risk for consumers with high credit scores. Servicers that are struggling with large numbers of mortgage deficiencies are now encountering issues with borrowers voluntarily electing to cease payment of their mortgage obligations."

As a supplement to the background information on this patent, VerticalNews correspondents also obtained the inventors' summary information for this patent: "In one aspect, a strategic default score is determined for an entity that characterizes a likelihood of the entity voluntarily electing to default on a loan is described. Data characterizing credit data and valuation data of an asset owned by the entity is received. The asset can be secured by a loan. Using the received data, the strategic default score is generated. The strategic default score characterizes a likelihood of the entity to voluntarily elect to default on the loan. Provision of the strategic default score can then be initiated.

"In one variation, the generating of the strategic default score comprises determining, using the received data, a ratio of a value of the loan to a current value of the asset, the value of the loan being obtained from the credit data, the value of the asset being obtained from valuation data, determining, based on the determined ratio, a segment of a plurality of segments that is associated with the entity, and determining, using at least one determined predictive model associated with the determined segment, the strategic default score of the entity, each segment of the plurality of segments being associated with one or more corresponding predictive models that are trained using historical credit data and historical valuation data for a plurality of individuals.

"The determining of the strategic default score further can further include selecting a first predictive model from the at least one predictive model. The selection can be based on a number of times the entity has defaulted on the one or more loans within a past predetermined period of time. The strategic default score can be generated by inputting the received data to the selected first predicted model.

"The first predictive model can be optimized using at least one divergence-based optimization algorithm. In some implementations, the first predictive model is a scorecard model. The optimized predictive model can be scaled so that the generated strategic default score is within a predetermined range. The voluntary election can characterize defaulting on the loan when the entity is capable of paying-off the loan.

"The strategic default score can characterize a likelihood of the entity to strategically default on the loan when continuing to pay other loans. The historical valuation data can comprise a value of the asset and a forecast of expected change in the value over a predetermined period of time. The provision of the strategic default score can comprise at least one of display, transmission, and storing of the strategic default score.

"In an interrelated aspect, a strategic default score is determined for an entity that characterizes a likelihood of the entity voluntarily electing to default on a loan is described. Data characterizing credit data of an entity and valuation data of an asset owned by the entity is received. The asset can be secured by a loan. Based on a current loan to value ratio is then determined using the received data, a segment of a plurality of segments that can be associated with the entity can be determined. By inputting the received data to a predictive model selected from at least two predictive models associated with the determined segment, the strategic default score of the entity is determined and provision of such score can then be initiated.

"In one variation, the generating of the strategic default score further comprises selecting a first predictive model from the at least one predictive model. The selection can be based on a number of times the entity has defaulted on the one or more loans within a past predetermined period of time. The strategic default score can be generated by inputting the received data to the selected first predicted model. The first predictive model can be a scorecard model.

"Articles of manufacture are also described that comprise computer executable instructions permanently stored on computer readable media, which, when executed by a computer, causes the computer to perform operations herein. Similarly, computer systems are also described that may include a processor and a memory coupled to the processor. The memory may temporarily or permanently store one or more programs that cause the processor to perform one or more of the operations described herein.

"The subject matter described herein provides many advantages. By identifying entities that are likely to strategically default on their loans, loan servicers can be proactive and offer alternatives (i.e., various treatments, etc.) to the entities in an effort to minimize their potential losses.

"The details of one or more variations of the subject matter described herein are set forth in the accompanying drawings and the description below. Other features and advantages of the subject matter described herein will be apparent from the description and drawings, and from the claims."

For additional information on this patent, see: Dornhelm, Ethan; Gao, Lu; Gaskin, Joanne; Wei, Yan; Backes, Tracy; Leverentz, Andrew. Strategic Loan Default Scoring. U.S. Patent Number 8751378, filed February 17, 2012, and published online on June 10, 2014. Patent URL: http://patft.uspto.gov/netacgi/nph-Parser?Sect1=PTO1&Sect2=HITOFF&d=PALL&p=1&u=%2Fnetahtml%2FPTO%2Fsrchnum.htm&r=1&f=G&l=50&s1=8751378.PN.&OS=PN/8751378RS=PN/8751378

Keywords for this news article include: Mortgage, Real Estate, Fair Isaac Corporation.

Our reports deliver fact-based news of research and discoveries from around the world. Copyright 2014, NewsRx LLC


For more stories on investments and markets, please see HispanicBusiness' Finance Channel



Source: Journal of Engineering


Story Tools






HispanicBusiness.com Facebook Linkedin Twitter RSS Feed Email Alerts & Newsletters