Data Science & AI
ZestFinance Introduces Big Data Model for Collections Scoring
Zest AI team
February 4, 2014
New industry-specific models can increase collections by 30%
LOS ANGELES, Calif.—February 4, 2014— ZestFinance, Inc., a technology startup that brought big data analysis to credit underwriting, today announced that it is extending its platform to now include collections scoring. Using ZestFinance’s new collections models, companies can increase their collections results while using 30% fewer resources.
ZestFinance’s collections models provide industry-specific scoring for collectors in auto financing, student lending, legal and healthcare.
Historically, collections scoring has been based on few pieces of data and simple math. ZestFinance’s groundbreaking scoring model uses thousands of data points and advanced machine learning algorithms to help determine which customers will pay back their loans. Using this model, collectors can easily determine which accounts have the highest potential for recovery and decide how to prioritize collections of those accounts to reduce operating costs.
“Big data is transforming financial services as we know it,” said Douglas Merrill, Founder and CEO of ZestFinance. “When we first started ZestFinance, we knew that applying Google-style big data analysis to credit underwriting would make a real difference in reducing the cycle of bad debt for millions of Americans, and it has. We want to do the same thing with the collections process. With advanced math and more data, we can radically improve companies’ collections efforts by focusing collector attention on borrowers who actually can repay their debt and we can create a better debtor experience.”
ZestFinance’s unique financial models consume thousands of raw data elements, including third-party data and data collected from borrowers. The models then transform this data into tens of thousands of useful meta-variables to assess key customer behaviors. ZestFinance’s team of math, computer science and artificial intelligence experts then analyze these variables to identify patterns, trends and unique insights.
For example, debtors who have made a number of small housing moves since they graduated from college repay less than those who have moved fewer times, even if they have moved a greater distance. Knowing this sort of data in advance maximizes wasted collector time and ultimately results in a better debtor experience.
In addition to licensing models, ZestFinance provides collectors with ROI reports and an operations dashboard. With the dashboard, companies can see how improvements in prioritization will affect their collections strategy. It also enables companies to model how changes in strategy will impact recoveries, staffing and profitability. ZestFinance’s reports create simplified and shareable reports that allow collectors to measure results against their overall profitability
November 24, 2021
Zest AI team
November 18, 2021
November 16, 2021