Mike Kresse | Monday, November 7, 2016
Collecting unpaid student loan debt is big business. Having tripled in value over the last 10 years, student debt now represents approximately $1.2 trillion of outstanding debt in the United States. And with nearly one in five borrowers at least 12 months behind in their payments, according to data published by the Education Department earlier this year, millions of borrowers are set for collection.
More than 20 collection agencies are currently working to convert severely delinquent student loans into good or rehabilitated borrowers. The objective is to get borrowers paying on a plan they can afford – even if this means paying as little as $5 per month. But with millions already a year behind, and millions more at various lesser stages of delinquency, where should a collection team start?
Using statistical modelling, collection teams can score borrowers in order to ascertain the likelihood of repayment or on-time payment, as well as the expected dollar value of the borrowers account and propensity to pay. This can give collectors a clearer understanding of those borrowers most likely to be converted into ongoing monthly payments and for whom they can rehabilitate a loan into good standing, thus allowing them to deploy their efforts more effectively.
Even better, statistical models used in this process do not need credit bureau data. That means collections costs are lower, and it enables accurate predictions to be created even for accounts with thin or limited credit history.
Ultimately, proper use of statistical modeling allows collectors to improve loan rehabilitation, reduce delinquencies, increase recoveries, reduce costs and allocate resources more effectively. How can you argue with that?
Learn how FIS’ institutional and corporate solutions can help you increase your competitive edge.Contact us