Data Science Supervised Learning Algorithms 2

Question 1

In a decision tree, what does a higher Gini impurity at a node indicate?

Accepted Answer

The classes are more mixed at that node

Answer

The node is more pure

Answer

The node is a leaf

Answer

The feature is continuous

Question 2

Which supervised algorithm is most prone to overfitting if grown without depth limits?

Accepted Answer

An unpruned decision tree

Answer

Naive Bayes

Answer

Linear regression

Answer

k-NN with large k

Question 3

What is the primary purpose of the kernel trick in support vector machines?

Accepted Answer

To enable linear separation in a higher-dimensional space without explicit mapping

Answer

To speed up gradient descent

Answer

To reduce the number of features

Answer

To normalize input data

Question 4

In logistic regression, what does the sigmoid function output represent?

Accepted Answer

A probability between 0 and 1

Answer

A class label directly

Answer

The residual error

Answer

The feature weight

Question 5

Why does k-nearest neighbors require feature scaling?

Accepted Answer

Distance calculations are dominated by large-range features

Answer

It uses gradient descent

Answer

It assumes Gaussian features

Answer

It needs one-hot encoding

Question 6

What does the 'naive' assumption in Naive Bayes refer to?

Accepted Answer

Features are conditionally independent given the class

Answer

The dataset is small

Answer

All classes are equally likely

Answer

The model ignores prior probabilities

Question 7

Which metric is most appropriate for evaluating a classifier on a heavily imbalanced dataset?

Accepted Answer

F1 score or AUC-PR

Answer

Accuracy

Answer

Mean squared error

Answer

R-squared