MCQ's on Supervised Learning

Which of the following is an example of supervised learning?

• Clustering

• Principal Component Analysis (PCA)

• Classification

• Association Rule Learning

In supervised learning, what is the primary goal?

• ○      To find hidden patterns in the data

• To maximize the distance between data points

• To map input data to output data

• To reduce the dimensionality of the data

What is overfitting in supervised learning?

• When the model performs well on training data but poorly on new data.

• When the model performs well on new data but poorly on training data.

• When the model performs poorly on both training and new data.

• When the model performs well on both training and new data.

Which of the following techniques is used to avoid overfitting in supervised learning models?

• Increasing the number of features

• Using a simpler model

• Decreasing the amount of training data

• Removing regularization

In which scenario would you use regression analysis in supervised learning?

• Predicting the category of a product review

• Identifying spam emails

• Forecasting the stock price of a company

• Grouping customers based on their purchase history

Which of the following is a linear model used for regression?

• Decision Tree

• Linear Regression

• Naive Bayes

• K-Nearest Neighbors (KNN)

What is the purpose of the validation set in supervised learning?

• To train the model

• To test the model after training

• To fine-tune the model's hyperparameters

• To deploy the model

 In the context of Lasso Regression, which of the following best describes the effect of the L1 regularization term?

• It minimizes the variance of the model.

• It encourages sparsity by driving some feature coefficients to zero

• It adds a penalty proportional to the square of the magnitude of coefficients.

• It always results in a more complex model than Ridge Regression.

Suppose you are fitting a linear regression model with both L1 (Lasso) and L2 (Ridge) penalties. This type of regression is known as:

• Elastic Net

• Bayesian Regression

• Partial Least Squares

• Principal Component Regression

When performing Ridge Regression, increasing the regularization parameter α\alphaα will generally:

• Increase the model's complexity and variance.

• Decrease the model's complexity and variance.

• Increase the model's complexity and bias.

• Decrease the model's complexity and bias.