Quiz
Lecture 3 - Decision Tree
This quiz has question types that open in the usual player.
Questions in this quiz (19)
1The ____________________ algorithm builds a prediction model by creating a series of splits in the tree?.
- ANaïve Bayes
- BNeural Network
- CK-Mean Clustering
- DEM Clustering
- EDecision Tree
2A _____________ is the topmost node in a tree structure in a decision tree algorithm.
- AChild node
- BLeaf node
- CParent node
- DBlack node
- ERoot node
3Decision tree algorithm can accommodate both categorical and continuous attributes as its input variables.
- ATrue
- BFalse
4Decision tree algorithm use information gain or gain ratio criteria to decide what attributes are most informative to build a tree structure, resulting in implicit _________________.
- ASampling
- BStandardization
- CAttribute selection
- DNormalization
- EAdaboosting
5A _____________ is the bottom node, from which no further branches grow.
- ARoot node
- BParent node
- CChild node
- DBlack node
- ELeaf node
6Decision tree algorithm is called a ______________ box algorithm because its learned tree structure can be represented as if-then rules to improve human readability and interpretation.
- ABlack
- BGray
- CWhite
7Decision tree algorithm can be used for classification purpose but not for regression analysis.
- ATrue
- BFalse
8Decision tree algorithm is faster and more scalable than Naïve Bayes algorithm.
- ATrue
- BFalse
9______________ is a technique in data mining that reduces the size of decision trees by removing sections of the tree that provide little power to reduce the complexity of the final classifier, and hence improve predictive accuracy.
- ACategorization
- BPruning
- CScaling
- DDiscretization
- EBranching
10Decision tree algorithm is a linear classifier in a sense that it can only classify linearly separable values of the class variable.
- ATrue
- BFalse
11_______________ measures the extent of uncertainty or randomness in a data set.
- AEntropy
- BInformation gain
- CMissing value
- DRegularity
- EError
12[blank_start]Information gain[blank_end] measures the change in entropy due to any amount of new information being added?
- AInformation gain
13Which of the following parameter CANNOT be used to control the growth of the tree?
- Amin_impurity_split
- Bmin_impurity_decrease
- Cmax_depth
- Dmin_samples_split
- ENone of the above
14____________________ parameter can be used to specify the minimum impurity value that the outcome of a split must satisfy.
- Amin_impurity_split
- Bmin_samples_leaf
- Ccriterion
- Dmin_sample_split
15_________________ or overtraining indicates that the prediction model greatly classify the training data set, but has bad prediction accuracy for the new data set.
- AScaling
- BRandomization
- CPruning
- DOverfitting
- ECategorization
16The default value of "criterion" parameter in decision tree algorithm is Entropy (or information gain).
- ATrue
- BFalse
17When the value of "min_samples_leaf" parameter is set to 20, any split that would produce a child node containing less than 20 cases is not accepted.
- ATrue
- BFalse
18It is strongly recommended that users prune (or simplify) a single decision tree model before they apply it for prediction purpose.
- ATrue
- BFalse
19_____________ parameter can be used to determine which metric the user likes to use to compute a split score for tree growth.
- Amin_impurity_split
- Bmin_samples_leaf
- Ccriterion
- Dmin_sample_split
- ENone of the above
Information
- Description
- 6500 Data Mining Quiz on Lecture 3 - Decision Tree, created by Brieanne Woodbury on 16/02/2021.
- Author
- Brieanne Woodbury
- Language
- English
- Views
- 1
- Tags
- Rating
- No ratings yet Rate this quiz