Choose

1. Decision Trees can be used for: O Classification O Regression O both Classification and Regression none of the above 2. Decision Trees have: O a root node Oleaf nodes O branches O all of the above a 3. Decision Trees are prone to: overfitting underfitting Operfect accuracy O being just like linear models 4. Limiting the growth of a Decision Tree can prevent overfitting. O True Fatir O False 5. Random Forests are not Ensembles of Decision Trees O True Fatima Sofy O False 6. Training is slow on Decision Trees because: the model is so complicated O the model takes a while to grow O the model requires a lot of resources O the training is not slow because of the simplicity of the model (unless its a lot of data) REVIOUS so 7. Decision trees are simple to understand, interpret, and visualize. True O False 8. An advantage of CART models is: Decision trees can be unstable because small variations in the data might result in a completely different tree being generated. This is called variance, which needs to be lowered by methods like bagging and boosting O Decision trees implicitly perform variable screening or feature selection Decision-tree learners can create over-complex trees that do not generalize the data well. Coverfitting) O Decision tree learners create biased trees if some classes dominate. 9. CART models can handle both numerical and categorical data. O True O False 10. CART models can not handle multi-output problems. o True O False 11. Decision trees require relatively little effort from users for data preparation O True Fatima Sofya False Fatima Solyani 12. Nonlinear relationships between parameters do not affect tree performance O True O False 13. It is not recommended to balance the data set prior to fitting with the decision tree O True O False 14 Boosting is a technique that can be used to improve the performance of decision tree learning True O False True Fatima Sofyani False Fatima Sofyani 13. It is not recommended to balonce the data sot prior to fitting with the decision troc True O False 14. Boosting is a technique that can be used to improve the performance of decision tree learning, O True O False 15. Greedy algorithms cannot guarantee to return the globally optimal decision tree. This can be mitigated by training multiple trees where the fatores and samples are randomly sampled with replacement o true Submit