Bank Reduces Debt Collection Costs Through Big Data Analytics

Analytics is a hot topic for a reason — it can save firms significant amounts of money by showing that the obvious process isn’t always the most cost-effective.

Mu Sigma, a consultancy based in Chicago and Bangalore, worked with a U.S. regional bank that saw its early stage delinquent credits jump to $45 million during the economic downturn. The bank wanted to see how it could maintain its 98 percent collection rate while reducing staffing and technology costs.

The consultants looked at the effectiveness of actions such as calls, IVRs and mailers to understand their impact, considered total available resources and mapped each collection strategy to recovery amounts. They concluded the bank was spending more than it needed.

“While some customers required multiple calls, there were many customers who just needed a reminder for paying back.” The bank and consultants developed an analytical model to determine the probability of collection and estimated the incremental impact of each action and then developed an optimization framework.

 The bank was able to shift some call center staff from early stage delinquency to late stage where they delivered a better return and reduce costs by $1 million without falling below the 98 percent collection rate for early stage delinquents.

Mu Sigma is now turning some of its best practices into products, said Tom Pohlman, head of values and strategy at the company

“We have a lot of platforms and products we are investing in as we build out the product part of Mu Sigma. We are filling a void in the analytic stack — it’s about mapping, and designing and planning your analytics journey with tools geared more to the C suite.”


Author: admin


Lost your password?