Recommendation systems are the focus of this Grade 10 Computer Science worksheet on artificial intelligence. Students examine how online systems use user behavior, interaction data, and patterns to decide which videos, songs, products, or other items to suggest. The lesson also develops an important idea: recommendations can change over time because a user's responses become new information for future suggestions.

Trace how personalized suggestions are created

Students follow a recommendation workflow beginning with signals such as clicks, watches, likes, skips, replays, and cart activity. They explore how these interactions can become features used to estimate preferences and rank possible recommendations. The lesson introduces collaborative filtering, including user-based and item-based approaches, alongside machine learning methods that rank candidate items according to predicted usefulness.

• Explain how interaction history can help estimate what a user may prefer.
• Distinguish user-based filtering from item-based filtering.
• Interpret ranking as deciding which candidate items should appear higher.
• Describe how user responses create feedback that can influence later suggestions.
• Explain why the cold start problem can affect users with little interaction history.

Apply the ideas to real recommendation scenarios

Students work with a dialogue question, matching activity, cloze exercise, labeled diagram, and explanatory reading passage before applying their knowledge through multiple-choice questions and true-or-false statements. Short-answer prompts ask students to explain why different users may receive different suggestions, identify useful interaction data, and describe the challenge created by limited history.

The extended response places students in the role of designing recommendations for a learning video app. They explain how videos could be suggested, how future recommendations could update in response to user behavior, and why a new learner may initially receive less accurate suggestions. This connects AI vocabulary to a realistic application rather than treating recommendation systems as an abstract concept.

Teacher support included

A separate Teacher Guide PDF includes learning objectives, teaching tips, discussion questions, and common mistakes. It can support class discussion around collaborative filtering, feedback loops, personalization, and the cold start problem.

Classroom use

Use this artificial intelligence worksheet after introducing machine learning applications, during a lesson on personalized digital systems, for independent review, or as a written concept check. The scenarios help students reason about why two people can use the same platform yet receive different recommendations and how continuing interactions can reshape what appears next.