An online film streaming company is interested in building a movie recommendation model by analyzing the historical film watching pattern of its customers. For example, analysis of the historical…

Question

Options

• AWhich modeling node would be used to build such a movie recommendation model?
• BTime Series node
• CApriori node
• DLinear node
• ECox node

• A
  12% (3)
• B
  4% (1)
• D
  76% (19)
• E
  8% (2)

Explanation

Note: There appears to be an error in the provided answer key. Based on the question content, the correct answer is C (Apriori node), not D (Linear node). Here is the accurate explanation:

Apriori is the correct choice because it is specifically designed for association rule mining - discovering "if A and B, then C" relationships in transactional data, which is exactly the pattern described. This technique (also called market basket analysis) powers the "customers who watched X also watched Y" style of recommendation system.

Why the others are wrong:

• Time Series node analyzes data points over time (e.g., stock prices, seasonal trends) - not item co-occurrence patterns.
• Linear node performs regression or classification on continuous/categorical variables - it predicts a numeric outcome, not item associations.
• Cox node is used for survival analysis (modeling time-to-event data like customer churn or clinical outcomes) - completely unrelated to recommendations.

Memory tip: Think of Apriori as the "grocery cart" algorithm - the classic example is "shoppers who buy bread and butter also buy milk." The streaming version is simply swapping groceries for movies. If the question mentions co-occurrence patterns or "also watched/bought," always reach for Apriori.

No community discussion yet for this question.