Client : Retail credit debt buyer (unsecured loans)
Project Objective : Produce daily operational strategy to maximize ROI & customer service quality
User Inputs on Zinia Front End:
1) Objective as maximizing net repayment
2) Customer decision journey as
- Customer pays or not
- Customer pays in full or installments
3) Business constraints such as
- Call intensity between x and y
- Letter intensity between x and y
What Zinia Does (automatically) :
1) Builds deep neural networks for customer payment profile.
2) Combines these models and simulates for the optimal call and letter intensity that maximizes the net repayments on the loan, within the business constraints set by user.
Results : Zinia produces daily operational strategy (i.e. which customers to call and letter). It projects an increase of 20% in total net repayments compared to the client's previous operational strategy (which was based on propensity scoring and rules).
