Success case

Prediction of the probability

of default for vehicle financing

The challenge

The bank has a credit scoring model for vehicle financing that allows predicting the probability of default for its customers based on certain financial information.

In general, transactional information of the customers is not available.


The objective is to provide a model capable of identifying customers with a higher probability of default in vehicle financing more accurately. This way, the bank can grant financing to customers with greater confidence.

As loans will be repaid more regularly, the bank will be able to predict its future profits and expenses with greater accuracy.

How have we done it?

  • XGBoost
  • Logistic Regression
  • Bivariate Analysis

Results provided

  • Increase in accuracy when predicting regular payment behavior by the applicant.
  • Reduction of loss risk through better applicant selection.