1. Learn
    2. /
  2. Courses
    3. /
  3. Credit Risk Modeling in R
  • 1

    Introduction and data preprocessing

    Free

    This chapter begins with a general introduction to credit risk models. We'll explore a real-life data set, then preprocess the data set such that it's in the appropriate format before applying the credit risk models.

  • 2

    Logistic regression

    Logistic regression is still a widely used method in credit risk modeling. In this chapter, you will learn how to apply logistic regression models on credit data in R.

  • 3

    Decision trees

    Classification trees are another popular method in the world of credit risk modeling. In this chapter, you will learn how to build classification trees using credit data in R.

  • 4

    Evaluating a credit risk model

    In this chapter, you'll learn how you can evaluate and compare the results obtained through several credit risk models.

Initializing

Exercise

Another round of pruning based on AUC

In the video you saw how the "full" logistic regression model with a logit link was being pruned based on the AUC. You saw how the variable home_ownership was deleted from the model, as it improved the overall AUC. After repeating this process for two additional rounds, the variables age and ir_cat were deleted, leading to the model:

log_3_remove_ir <- glm(loan_status ~ loan_amnt + grade + annual_inc + emp_cat, family = binomial, data = training_set)

with an AUC of 0.6545. Now, it's your turn to see whether the AUC can still be improved by deleting another variable from the model.

Instructions

100 XP
  • Delete one variable at a time in the model log_3_remove_ir, Remember that you should be using the default link function (logit).
  • Make probability of default-predictions for each of the models you created.
  • Use function auc() using test_set$loan_status as a first argument and the predictions for each of the four models as a second argument to obtain the AUC's for each model.
  • Copy the name of the object (as given in the first question of this exercise) that represents the model with the best AUC.