MCQs

1. What is the main purpose of TF-IDF in this project?
a. To predict user ratings
b. To convert movie genres into numerical vectors
c. To deploy the model
d. To clean missing values

Answer: b. To convert movie genres into numerical vectors
TF-IDF allows genre text to be represented numerically so similarity between movies can be calculated.

2. Why is KNN preferred over a full similarity matrix?
a. It improves UI design
b. It reduces memory usage and computation cost
c. It increases model accuracy automatically
d. It removes preprocessing steps

Answer: b. It reduces memory usage and computation cost
KNN computes similarity only when needed, avoiding large precomputed matrices.

3. What does the hybrid score represent?
a. Random movie ranking
b. Genre similarity only
c. Average rating only
d. A combination of genre similarity and average rating

Answer: d. A combination of genre similarity and average rating
This ensures recommendations are both relevant and well-rated.

4. Why is the clean_title column created?
a. To remove duplicate ratings
b. To improve title matching for user input
c. To calculate similarity
d. To store release year

Answer: b. To improve title matching for user input
Removing the year makes searches flexible and user-friendly.

5. What is the main advantage of using Gradio?
a. It replaces machine learning logic
b. It requires frontend coding
c. It quickly converts Python functions into interactive apps
d. It stores datasets

Answer: c. It quickly converts Python functions into interactive apps
Gradio enables fast deployment without frontend development.