NEW
Font size
WorksheetsITS665_Chap4
Total questions: 20
Worksheet time: 10mins
Which of the following is a characteristic of supervised learning?
Does not require training data
Focuses on clustering
Involves labeled data
Uses unlabeled data
What is the purpose of attribute selection in Decision Trees?
To visualize the data
To classify data into clusters
To determine the best splitting attribute
To reduce the size of the dataset
Which algorithm is commonly used for Decision Tree induction?
Support Vector Machines
Apriori
Hunt's Algorithm
K-means
Which of the following is an example of unsupervised learning?
Naïve Bayes
Logistic Regression
K-means Clustering
Decision Trees
What is the formula for calculating accuracy in classification?
Correct samples / Total samples
Total samples / Correct samples
Correct samples + Total samples
Total samples - Correct samples
What type of data does supervised learning use?
Structured data
Random data
Labeled data
Unlabeled data
Which of the following is a continuous attribute?
Marital Status
Class
Refund
Taxable Income
What does a Decision Tree model output?
A set of rules
A single value
A graph
A list of attributes
What is the primary goal of classification in data mining?
Group similar items
Predict class labels accurately
Visualize data
Normalize data
Which algorithm is NOT associated with supervised learning?
Decision Tree
K-Means
K-Means
Naïve Bayes
In a decision tree, what does each leaf node represent?
An attribute
A decision
A class label
A class label
What is used to measure the impurity of a node in a decision tree?
Accuracy
Entropy
Precision
Recall
A decision tree’s root node is based on which attribute selection?
Random
Information Gain
Gini Index
Gain Ratio
What is the output of a decision tree algorithm?
Association rules
A tree structure
A regression equation
Clusters
What type of data is suitable for unsupervised learning?
Labeled data
Unlabeled data
Both labeled and unlabeled data
None of the above
When do you stop splitting in a decision tree algorithm?
All records belong to one class
Max tree depth reached
Attributes are exhausted
All of the above
What is the final outcome of applying a decision tree to test data?
A report
Predicted labels
Clusters
Association rules
What is an advantage of rule extraction from decision trees?
Complexity
Clarity
Generalization
Randomness
In binary splitting, how many subsets does a continuous attribute divide into?
1
2
3
4
What does the term "overfitting" mean in a decision tree model?
The model is too simple
The model generalizes well
The model fits noise in the training data
The model is accurate
