How does Adobe Target Recommendations select products for "Most Viewed" criteria?

Question

Options

• ABased on user-defined rules
• BUsing machine learning to identify trends
• CBy analyzing historical product view data
• DBy prioritizing high-profit-margin products

• A
  4% (1)
• B
  11% (3)
• C
  81% (22)
• D
  4% (1)

Explanation

Adobe Target's "Most Viewed" criteria works by counting and ranking products based on how many times each item has been viewed across historical session data - making C correct. This is a straightforward aggregation algorithm, not machine learning, which eliminates B (ML-driven approaches are used in criteria like "Recommended for You" or collaborative filtering). A is wrong because "Most Viewed" is an automated, data-driven algorithm - user-defined rules apply to inclusion/exclusion filters, not the core selection logic. D is wrong because Target has no inherent knowledge of profit margins unless explicitly fed that data as a custom attribute, and even then, "Most Viewed" doesn't use it.

Memory tip: Think of "Most Viewed" as a simple scoreboard - it just counts page view events from your analytics history and ranks accordingly. If it sounds like a spreadsheet can do it, it's probably historical data aggregation (C), not ML (B).

No community discussion yet for this question.