Data Science Supervised Learning Algorithms 4

Question 1

What is the bias-variance tradeoff?

Accepted Answer

Balancing underfitting (high bias) against overfitting (high variance)

Answer

The bias-variance tradeoff balances errors from overly simple models (bias) and overly complex ones (variance).

Question 2

Why is cross-validation preferred over a single train-test split?

Accepted Answer

It gives a more robust estimate of model performance across folds

Answer

Cross-validation averages performance over multiple folds, giving a more reliable generalization estimate.

Question 3

In multiclass classification, what does the softmax function produce?

Accepted Answer

A probability distribution over all classes summing to 1

Answer

Softmax converts raw scores into a probability distribution across classes that sums to one.

Question 4

What is a key disadvantage of k-nearest neighbors at prediction time?

Accepted Answer

It is computationally expensive because it stores and searches all training data

Answer

k-NN is a lazy learner that searches the entire training set at inference, making prediction slow.

Question 5

Which scenario most likely indicates an underfitting model?

Accepted Answer

High training error and high test error

Answer

High error on both training and test sets indicates the model is too simple, i.e., underfitting.

Data Science Practice Test