Data Science Supervised Learning Models 3

Question 1

What is the bias-variance tradeoff?

Accepted Answer

A balance between underfitting and overfitting errors

Answer

A tradeoff between speed and memory

Answer

A choice between L1 and L2 penalties

Answer

A method to balance classes

Question 2

In k-nearest neighbors, what happens as k increases?

Accepted Answer

The decision boundary becomes smoother

Answer

The model overfits more

Answer

Training time grows exponentially

Answer

Features are dropped

Question 3

Which ensemble method builds trees sequentially, each correcting the previous one's errors?

Accepted Answer

Gradient boosting

Answer

Random forest

Answer

Bagging

Answer

Voting classifier

Question 4

What does a high recall but low precision indicate?

Accepted Answer

Many false positives but few false negatives

Answer

Many false negatives

Answer

Perfect classification

Answer

No predictions made

Question 5

Why is feature scaling important for SVM and KNN?

Accepted Answer

They rely on distance calculations sensitive to feature magnitude

Answer

They cannot handle text

Answer

They require integer inputs

Answer

They ignore feature values

Question 6

What is the role of the learning rate in gradient descent?

Accepted Answer

It controls the step size of weight updates

Answer

It sets the number of features

Answer

It defines the loss function

Answer

It counts training samples

Question 7

Which model assumes feature independence given the class label?

Accepted Answer

Naive Bayes

Answer

Random forest

Answer

Neural network

Answer

SVM