Practice Evaluation Of Recommender Systems (11.6) - Recommender Systems

Practice: Evaluation of Recommender Systems

Lesson 11.6Recommender Systems

Practise this section

10 questions

Flashcard drill
4 cards from this section. Quick, good the night before a test.
Exercise
6 questions · about 4 min · pass mark 70%. Hints available.
Sign up to start the exercise
Quiz
4 questions · about 3 min · pass mark 70%. Hints available.
Sign up to start the quiz

6 sample questions

Question 1.
What is the purpose of offline evaluation?
Show hintHide hint
Think about how past data can help inform us.
Question 2.
Define precision in the context of recommender systems.
Show hintHide hint
Consider the accuracy of the recommendations.
3Question 3.
What does precision measure?
- The total number of recommendations
- The ratio of correct recommendations to total recommendations
- The time users spend on recommendations
Show hintHide hint
Think about how often the recommendations are correct.
4Question 4.
True or False: Recall is concerned with how many relevant items were actually shown to users.
- True
- False
Show hintHide hint
Consider what it means by 'relevant' items.
Question 5.
Create a case where offline evaluation indicates a very high precision, but the online evaluation shows a very low click-through rate. Discuss possible reasons.
Show hintHide hint
Reflect on how user preferences can change over time.
Question 6.
Using a hypothetical dataset, calculate RMSE given the following actual and predicted ratings: Actual: [5, 4, 3, 2], Predicted: [5, 3, 4, 1]. What does this RMSE say about the model’s accuracy?
Show hintHide hint
Consider the importance of smaller RMSE values.

6 more questions in this section. Enroll free to practise them all.