New "ScoreText" Analyzes Call Center, Other Unstructured Data

Breakthrough Appreciation Leverages All Available Customer Data

SAN FRANCISCO, Calif. AND BELLEVUE, Wash. – January 11, 2005 – LoanPerformance, the leader in residential mortgage data and analytics, and Intelligent Results, a leader in customer relationship analytics solutions, today jointly announced the availability of ScoreText, a new predictive modeling solution with wide application across the mortgage industry. ScoreText integrates structured data with unstructured text data, enabling mortgage servicers to better understand and more accurately predict customer behavior in servicing and collection efforts.

Historically, mortgage servicers have identified and prioritized potential problem loans using structured numeric data. However, until now, they have not been able to systematically access information and observations generated by other forms of interaction with borrowers. This mixed-data analytics approach combines free-form text from lender’s and collector’s notes, call centers, CRM systems and borrower emails, with structured data from traditional sources including credit scores, payment histories, loan balances, customer demographics, property record information, collections systems, and account master files.

“Today’s best predictive models only incorporate about 20% of the available data,” said Richard Harmon, Ph. D., senior vice president, scoring analytics and services at LoanPerformance. “By exploiting the available unstructured data that makes up the other 80%, mortgage servicers can not only improve their ability to predict customer behavior, but can have a much better understanding of the key factors differentiating behavior. We believe many servicers will be able to improve their current loss mitigation performance by as much as 50%.”

“Extracting this textual data and incorporating it into predictive loss mitigation models provides servicers with a much more powerful tool to determine which loans will cure themselves and which should be handled using forbearance, short sales, foreclosure or other methods,” added Harmon.

The ScoreText solution was jointly developed by LoanPerformance, which currently tracks the monthly prepayment and delinquency performance of 46 million loans, and Intelligent Results, a company that has already successfully utilized a mixed-data approach to improve the servicing and collection functions in the credit card, auto and other consumer lending industries. For example, one credit card issuer improved annual returns by $4.2 million using Intelligent Results’ mixed-data models to target early stage settlement offers.

“Current collections and recovery processes utilize both automated systems and human interaction to determine a delinquent borrower’s ability to repay and the type of workout the servicer should pursue,” said Craig Focardi, senior analyst at TowerGroup. “But important information is locked in unstructured memo fields and it is expensive to add new data fields to servicing systems. This unique offering can help mortgage servicers by adding greater predictive ability to existing collections and loss mitigation systems and processes. This helps keep more borrowers in their homes and lower mortgages delinquencies and foreclosures.”

While some words captured in customer communications are intuitively signs of trouble, like “fired” or “bankruptcy,” the power of mixed-data analytics modeling lies in its ability to identify relationships between seemingly innocuous words like “motorcycle” or “roommate” and loan delinquencies and defaults. Mixed-data analytics involves a four-step process where text is cleaned, categorized, extracted and then modeled for application across a wide spectrum of servicing functions including collections management, loss mitigation, fraud, high-risk properties, customer complaint management, customer retention, and customer cross-sell.

“The mortgage industry represents a large, untapped market for the use of mixed-data analytics,” said Stan Shull, vice president, business development at Intelligent Results. “Combining LoanPerformance’s leading data and analytics expertise with Intelligent Results’ customer relationship analytics technology delivers a significant bottom line benefit to mortgage servicers.”

About LoanPerformance
LoanPerformance is the leader in residential mortgage performance data and credit risk decision-support tools for mortgage originators, servicers, securities issuers and investors. LoanPerformance’s industry-standard databases track the delinquency and prepayment performance of 46 million individual mortgage payments per month, representing 90% of outstanding prime mortgages, 75% of outstanding securitized nonprime mortgages, 80% of publicly traded non-agency mortgage securities, and 80% of bank-owned home equity loans and lines of credit. LoanPerformance proprietary databases and suite of predictive prepayment and risk modeling solutions enable clients to make informed decisions about their credit risk, loss mitigation and securitization strategies. LoanPerformance is privately-held and headquartered in San Francisco, CA. ScoreText is a trademark of LoanPerformance.

About Intelligent Results
Intelligent Results is the leading provider of customer relationship analytics solutions which use mixed-data to analyze and better predict customer behavior in marketing, collections and recovery. Clients throughout the financial services, consumer packaged goods and telecommunications industries, including four of the top ten US banks, use Intelligent Results’ solutions to generate better customer level decisions and drive their businesses forward. By combining traditional structured data from account master files, credit records and transactions, with free-form customer communications data, such as CRM, call center and collections notes, Intelligent Results’ solutions provide deeper insight into customer behavior and deliver 20 to 60 percent more accurate predictive models than traditional solutions. Intelligent Results is privately-held and based in Bellevue, WA.

©2005, LoanPerformance. All Rights Reserved.

http://www.loanperformance.com/pressreleases/pr011105.aspx
Copyright ©2008 LoanPerformance