QUESTION 14

Algoritm for Decision Tree Induction

Create a new node

Find the best split

Determine class label to be assigned to a leaf node

_______________________.

	a.	repeat step 1 / repeat step 2
	b.	look for another split
	c.	repeat steps 1-3 / stop
	d.	terminate the tree-growing process

4 points

QUESTION 15

Which of the following is NOT a measure of node impurity:

	a.	Classification error
	b.	Entropy
	c.	Gain Ratio
	d.	Gini Index

4 points

QUESTION 16

Rule-based classifiers can be characterized by the following properties

	1.	Decision Rule Set
	2.	Exhaustive Rule Set
	3.	Mutually Exclusive Rule Set
	4.	Partial Rule Extraction

4 points

QUESTION 17

Which of the following is NOT a characteristic of a Nearest Neighbor Classifier:

		Nearest neighbor classifiers is part of a more general technique known as building classifiers
		Nearest neighbor classifiers make their prediction based on local information
		Nearest neighbor classifiers can produce decision boundaries of arbitrary shapes
		Nearest neighbor classifiers can handle the presence of interacting attributes

4 points

QUESTION 18

Naive Bayes classifiers are probabilistic classification models that are able to quantify the uncertainty in predictions by providing posterior probability estimates.

True

False

4 points

QUESTION 19

In one sentence, define support vector machine (SVM)

Words:0

QUESTION 20

Which of the follow can be constructed for the ensemble of classifiers (Select all that apply)

	a.	By manipulating the training set
	b.	By manipulating the subsets
	c.	By manipulating the learning algorithms
	d.	By manipulating the class labels
	e.	By manipulating the input features

4 points

QUESTION 21

A brute-force approach for finding frequent itemsets is to determine the support count for every ________________ in the lattice structure

4 points

QUESTION 22

The strength of an association rule can be measured in terms of its __________ and ___________

		algorithm / candidates
		transactions / rules
		support / confidence
		x / y

4 points

QUESTION 23

The Apriori Principle says If an itemset is frequent, then all of its subsets must also be frequent

True

False

4 points

QUESTION 24

The computational complexity of the Apriori algorithm, which includes both its runtime and storage, can be affected by the following factors (Select all that apply)

		Support threshold
		Number of Items (Dimensionality)
		Number of Transactions
		Support counting

4 points

QUESTION 25

An ___________ is a compressed representation of the input data. It is constructed by reading the data set one transaction at a time and mapping each transaction onto a path in the __________.

Hint: one term fits both blanks