Q. In the context of feature engineering, what does 'one-hot encoding' achieve?
A.
Reduces dimensionality
B.
Converts categorical variables into a numerical format
C.
Eliminates multicollinearity
D.
Increases the number of features exponentially
Solution
One-hot encoding converts categorical variables into a numerical format by creating binary columns for each category, allowing algorithms to process them effectively.
Correct Answer:
B
— Converts categorical variables into a numerical format
Q. What does the term 'overfitting' refer to in the context of model selection?
A.
A model that performs well on training data but poorly on unseen data
B.
A model that is too simple to capture the underlying data patterns
C.
A model that uses too many features
D.
A model that is trained on too little data
Solution
Overfitting occurs when a model learns the training data too well, capturing noise instead of the underlying pattern, leading to poor performance on unseen data.
Correct Answer:
A
— A model that performs well on training data but poorly on unseen data
Q. What is the purpose of normalization in feature engineering?
A.
To increase the range of feature values
B.
To ensure all features contribute equally to the distance calculations
C.
To reduce the number of features
D.
To eliminate outliers
Solution
Normalization adjusts the scale of feature values to ensure that they contribute equally to distance calculations, which is crucial for algorithms sensitive to feature scales.
Correct Answer:
B
— To ensure all features contribute equally to the distance calculations
Q. Which model selection technique involves comparing multiple models based on their performance on a validation set?
A.
Grid Search
B.
Feature Engineering
C.
Data Augmentation
D.
Dimensionality Reduction
Solution
Grid Search is a model selection technique that systematically works through multiple combinations of parameter tunes, cross-validating as it goes to determine which tune gives the best performance.
