Client : P2P Lender (unsecured loans)
Project Objective : Individualized pricing of loans so that it works best for the client and their customers
User Inputs on Zinia Front End:
1) Objective as maximizing loan returns
2) Customer decision journey as
- Accept or Reject the customer loan
- Customer takes up the offer or not
- Customer loan performance
3) Business constraints such as
- Interest Rate between x and y %
- Customer Overall indebtedness after loan smaller than a policy threshold
What Zinia Does (automatically) :
1) Builds deep neural networks for customer behaviors such as price sensitivity to the loan, customer default and pay back.
2) Combines these models and simulates for the optimal price (interest rate) that maximizes the net returns on the loan, within the business constraints set by user.
Results : Zinia projects an increase of 25.6% in total net returns achieved as more than 2 years worth of historical data goes through the self learning algorithms