Recommendation systems are the focus of this Grade 9 Computer Science worksheet, helping students explain how online platforms use data patterns, algorithms, and user preferences to personalize content. Students explore ranking, suggestions, behavioral data, content-based filtering, and collaborative filtering through familiar recommendation scenarios. :contentReference[oaicite:0]{index=0}

Connect AI personalization to everyday online experiences

The lesson shows how recommendation systems estimate what a user may want to watch, read, or purchase by examining patterns in recorded behavior. Students work with signals such as likes, skips, ratings, watch time, clicks, and purchase history, then consider how an algorithm can use those signals to rank items from more likely to less likely matches.

Students also examine why recommendations are not fixed. As new behavior is recorded, the system can update its estimate of a user's preferences and change future suggestions.

Compare two recommendation approaches

• Defining recommendation, preference, suggestion, and algorithm in context
• Explaining how data patterns help rank items for an individual user
• Identifying content-based recommendations that use item features such as genre or topic
• Recognizing collaborative recommendations that use behavior from people with similar interests
• Evaluating which user data or patterns could support a recommendation scenario

The distinction between the two filtering approaches is reinforced through examples. Content-based filtering connects new items to features of content a user already preferred, while collaborative filtering considers choices made by users with similar behavior.

Students reason about how recommendations change

A dialogue, matching activity, cloze passage, labeled diagram, and reading passage establish the vocabulary and process. Multiple-choice and true-or-false questions ask students to identify ranking signals, preferences, algorithms, and filtering approaches. Short-answer prompts require students to explain what data a recommendation system might collect and why an algorithm is used instead of presenting items randomly.

The extended response applies the concepts to a student whose viewing habits shift from fantasy videos to science clips. Students explain how future recommendations could change and identify the data or patterns the system could use.

Teacher support included

A separate teacher guide PDF includes learning objectives, teaching tips, discussion questions, and common mistakes. Use this AI recommendation systems worksheet during an artificial intelligence unit, after introducing data-driven predictions, or as practice connecting machine learning concepts to personalized online content.