Loan Fraud Prevention
Objective
- To develop an effective, easy to use auto loan credit assessment tool for a big auto dealership.
- In case of risky applications, the tool should be able to suggest ways to cover the credit exposure (e.g. higher down payment, high interest rate etc.)
Methodology
- Developed statistical models on historical data to predict charge-off/ early pay-off and other loss producing behavior propensity.
- Developed an easy to use MS Excel dashboard tool with the model algorithms built in.
- The tool takes an application’s profile details as input and gives scores to it on various risk propensities.
Impact
- The business has an informed way to accept/ reject applications based on what behavior to expect.
- By using the recommendations to improve risk profile, they have a way to improve the portfolio quality without increasing rejection rates.
- Good: Any customer whose application is approved by the bank.