400 Sun - 10th May

What is the main purpose of feature scaling in machine learning?

• To remove missing values

• To help models perform better

• To clean the dataset

• To increase the number of rows

What does it mean when a feature is standardized?

• It is converted to text

• It is removed from the dataset

• It has mean = 0 and standard deviation = 1

• It is stored in a new file

Which of the following models is sensitive to feature scaling?

• Decision Tree

• Logistic Regression

• Random Forest

• None of the above

Which of these techniques is used to normalize or scale data?

• OneHotEncoder

• LabelEncoder

• StandardScaler

• ValueCounter

When should you apply scaling in a machine learning pipeline?

• Before train-test split

• After making predictions

• After splitting and only on training data

• Never

What is the purpose of splitting data into training and testing sets?

• To save storage

• To test model performance on new data

• To increase rows

• To remove missing values

What is a common ratio used for splitting train and test sets?

• 80:20

• 50:50

• 90:10

• 10:90

What happens if we test and train a model on the same data?

• It performs better

• It gives accurate real-world predictions

• It may overfit

• It reduces training time

Which Python library provides the train_test_split function?

• numpy

• pandas

• matplotlib

• sklearn

What is overfitting in machine learning?

• When the model performs poorly

• When the model performs well on train data but poorly on test data

• When the model stops training

• When the data is corrupted