Afni, Inc.

Predictive analytics prioritizes the debts most likely to be paid for a more profitable business

Published on 24-Jan-2014

"We had not anticipated just how accurate a predictor ZIP code information could be. Analysis has revealed that neighborhoods with higher-than-average incomes and house values are strong indicators of good payers — enabling us to focus our efforts on cases with the highest probability of returns." - Barry Gamage, director of analytics

Customer:
Afni, Inc.

Industry:
Financial Markets

Deployment country:
United States

Solution:
BA - Business Analytics, BA - Predictive Analytics, Big Data & Analytics, Big Data & Analytics: Customers, Big Data & Analytics: Operations/Fraud/Threats, Smart Work, Smarter Computing, Smarter Planet

Overview

Headquartered in Bloomington, Illinois, Afni, Inc. delivers a comprehensive set of solutions, including customer acquisition and enrollment; customer care and loyalty; up-sell and cross-sell; and accounts receivable and subrogation services. Afni employs 4,000 people and is a leading provider of contact center outsourcing for enterprises in the United States and the Philippines.

Business need:
To keep its debt-recovery services profitable, debt-collection firm Afni, Inc. needed to predict which individuals are most likely to settle their debts.

Solution:
Afni achieves higher returns for each dollar spent on debt collection by using complex predictive models to segment and score debtors based on their personal and financial histories.

Benefits:
Across 108 projects associated with the analytics solution, Afni identified USD8 million in potential cost savings, made possible by focusing on debtors most likely to pay rather than wasting time and money on phone calls and letters that aren’t likely to yield results.

Case Study

Headquartered in Bloomington, Illinois, Afni, Inc. delivers a comprehensive set of solutions, including customer acquisition and enrollment; customer care and loyalty; up-sell and cross-sell; and accounts receivable and subrogation services. Afni employs 4,000 people and is a leading provider of contact center outsourcing for enterprises in the United States and the Philippines.

The Opportunity
To keep its debt-recovery services profitable, debt-collection firm Afni, Inc. needed to predict which individuals are most likely to settle their debts, devoting more calls, letters and research to sure bets rather than deadbeats.

What Makes It Smarter
Afni achieves higher returns for each dollar spent on debt collection by using complex predictive models to segment and score debtors based on their personal and financial histories. The solution analyzes personal information, credit scores and census data — including average income, house value and level of education in the debtor’s ZIP code — to predict each debtor’s probability of repayment.

Real Business Results
By boosting collection success rates and eliminating outsourced analytics costs, the predictive analytics solution yielded a 6-figure savings for the receivables management team. For the insurance team, the solution helped drive a 15 percent increase in successful subrogation, or collection of payments from uninsured drivers who were at fault in an auto accident. Afni also reduced the manual work of closed-file reviews — older subrogation cases that customers want to reopen for debt recovery — by 94 percent, allowing the company to offer the service at a more competitive price. Across 108 projects associated with the analytics solution, Afni identified USD8 million in potential cost savings, made possible by focusing on debtors most likely to pay rather than wasting time and money on phone calls and letters that aren’t likely to yield results.


For More Information
Please contact your IBM representative or IBM Business Partner.
Visit us at ibm.com/spss.

To learn more about Afni, Inc., visit www.afni.com.

Products and services used

IBM products and services that were used in this case study.

Software:
SPSS Modeler Server, SPSS Modeler

Legal Information

© Copyright IBM Corporation 2014 IBM Corporation Software Group Route 100 Somers, NY 10589 Produced in the United States of America January 2014 IBM, the IBM logo, ibm.com and SPSS are trademarks of International Business Machines Corp., registered in many jurisdictions worldwide. Other product and service names might be trademarks of IBM or other companies. A current list of IBM trademarks is available on the Web at “Copyright and trademark information” at www.ibm.com/legal/copytrade.shtml. This document is current as of the initial date of publication and may be changed by IBM at any time. Not all offerings are available in every country in which IBM operates. The performance data discussed herein is presented as derived under specific operating conditions. Actual results may vary. THE INFORMATION IN THIS DOCUMENT IS PROVIDED “AS IS” WITHOUT ANY WARRANTY, EXPRESS OR IMPLIED, INCLUDING WITHOUT ANY WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND ANY WARRANTY OR CONDITION OF NON-INFRINGEMENT. IBM products are warranted according to the terms and conditions of the agreements under which they are provided.