Optimization at Predictive Analytics World Boston, Sept 27-Oct 1, 2015, we asked Werner Britz, Head of Decision Science at RCS Group, a few questions about his work in predictive analytics.
Q: In your work with predictive analytics, what behavior do your models predict?
A: The predictive model developed and part of business operations are Application and Behavior models predicting risk. There are a number of different Behavior Risk Scorecards in play depending on the portfolio and delinquency level. Forward Roll Behavior Risk Scorecards are actively used in collections strategies. At customer solicitation we utilize Response Scorecards to cut cost and to market more effectively to the correct customers.
Q: How does predictive analytics deliver value at your organization? What is one specific way in which it actively drives decisions?
A: Differentiating better between good and bad prospective customers is where the real value op predictive analytics starts. Predictive models form the cornerstone of the front-end Risk Assessment Solution and play a major part in determining the product offering. Taking the correct action on booked customers is made possible by predicting how the customer is going to behave in the future.
Q: Can you describe a successful result, such as the predictive lift of your model or the ROI of an analytics initiative?
A: Redevelopment of Loans Application Scorecards has made it possible to either increase the acceptance rate for the same bad rate or accept the same volumes but with a much lower bad rate. The business decision would depend greatly on which solution in the above mentioned range would increase advances and drive down charge-offs.
Q: What surprising discovery have you unearthed in your data?
A: Since Predictive modelling is the process of classify homogenous groups together and treating/offering them the same, the decomposition of these homogenous groups together with a slightly different risk/product modelling variable could further enhance product offering and competitive edge.
Q: Sneak preview: Please tell us a take-away that you will provide during your talk at Predictive Analytics World.
A: Double digit lift in Recovery rate made possible by engaging predictive analytics and optimization theory.
———————
Don’t miss Werner Britz’s conference presentation, Recoveries: External Debt Collection Optimization on Monday, September 28, 2015 from 2:40pm – 3:25pm at Predictive Analytics World Boston. Click here to register to attend.
By: Eric Siegel, Founder, Predictive Analytics World