Practice Offline Evaluation (11.6.1) - Recommender Systems - Data Science Advance

Practice: Offline Evaluation

Lesson 11.6.1Recommender Systems

Practise this section

8 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
2 questions · about 1 min · pass mark 70%. Hints available.
Sign up to start the quiz

6 sample questions

Question 1.
What is the purpose of offline evaluation in recommender systems?
Show hintHide hint
Consider how we test algorithms without live data.
Question 2.
Define precision in the context of recommender systems.
Show hintHide hint
Think about how many of your recommendations were liked.
3Question 3.
What is the main purpose of offline evaluation?
- To gather live user feedback
- To simulate performance with historical data
- To collect new interaction data
Show hintHide hint
Think about how we can check the system before it is live.
4Question 4.
True or False: Recall measures how many actual relevant items were recommended.
- True
- False
Show hintHide hint
Recall captures the successes in finding relevant recommendations.
Question 5.
Given a recommendation system that suggested 20 items, with 10 being relevant and only 6 being recommended correctly, calculate precision and recall.
Show hintHide hint
Use the formulas to find these metrics.
Question 6.
Discuss how varying the threshold for recommendations can impact precision and recall.
Show hintHide hint
Think of how a tighter or looser net catches more or fewer fish.

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