Understanding Decision Trees in Machine Learning

To segment the predictor space into simple regions (correct)

To create complex boundaries for continuous variables

To maximize entropy in the data set

To minimize information gain from the split

Reduce overfitting by limiting tree depth (correct)

Maximize impurity in terminal nodes

Increase overfitting by expanding tree depth

Minimize information gain from root splits

Aggregating the results of identical models

Creating multiple decision trees trained on different bootstrap samples (correct)

Creating a single decision tree trained on multiple bootstrap samples

Training decision trees on the entire data set without sampling

<p>They are turned into categorical variables based on a certain value</p> Signup and view all the answers

<p>Aggregating the results of different models to improve predictive performance</p> Signup and view all the answers