Dividing the entire data set into a training data set and a validation training set is a key step in one approach to ________ the data.
A) declassifying
B) purifying
C) removing invalid observations from
D) training
E) avoid overfitting

Question

Quizplus · Accepted Answer

One approach to avoid overfitting is to divide the entire data set into a training data set, which is used to make splits based on the specified minimum split size/leaf purity termination criterion, and a validation data set, which is used as an additional criterion to decide when to stop making splits.

Dividing the Entire Data Set into a Training Data Set