Session Ready
Exercise

Evaluating regression models

You are quickly getting the hang of evaluating Machine Learning models in R! Let's switch now to regression models, as these are quite common in Machine Learning interviews.

In this exercise, you are going to train a Support Vector Machine with a Radial Basis Function (RBF) kernel to predict the Overall score of a FIFA soccer player based on four game performance indicators. A simplified version of the FIFA19 dataset containing information about 1,000 players is already available in your workspace. The data has been split into 75% training and 25% testing.

As before, the caret and Metrics packages have been preloaded and a 10-fold cross-validation caret train control object named cv10 has been created too.

Let's go ahead and evaluate the performance of our SVM model.

Instructions 1/4
undefined XP
  • 1
  • 2
  • 3
  • 4
  • Train an SVM with RBF kernel in caret (method name is "svmRadial") to predict the Overall score of a FIFA player from all other variables using the training data and the 10-fold cross-validation object. Save the result as mdlSVM.