Build your own detection model
Let's combine the tools we've seen in this chapter. The credit transfer dataset from the previous exercises was split in a training set and a test set with the same class imbalance. Next, SMOTE was applied on the training set. You'll build a classification tree model on both the original imbalanced training set and the re-balanced training set. Finally, both models will be compared on the same test set.
The rpart
and caret
libraries are already loaded in your workspace. Don't hesitate to refer to the slides to complete this exercise.
This exercise is part of the course
Fraud Detection in R
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Train the rpart algorithm on the original training set and the SMOTE-rebalanced training set
model_orig <- ___(___, data = ___)
model_smote <- ___(___, data = ___)