In *Lesson 4: Shoe Recommender*, students tested an app that helps people choose what shoes to wear. What was the goal of this app?

• To collect shoe prices

• To help users decide what shoes to wear

• To design new shoes

• To predict shoe sales

In *Lesson 4: Shoe Recommender*, students explored how the app made choices. How did this first version make its decisions?

• Using patterns from data

• Using if–else rules written by humans

• Copying other users’ choices

• Random guessing

In *Lesson 4: Improved Shoe Recommender*, students improved the app by adding a survey. What new feature did this version include?

• A larger shoe collection

• Collecting user survey data

• Stopping all questions

• Using no rules at all

In *Lesson 4: Improved Shoe Recommender*, students analyzed how survey data improved results. Why does collecting user survey data help?

• It lets the model learn from real user patterns

• It makes the app faster

• It removes the need for any data

• It deletes wrong predictions

In *Lesson 4: Shoe Recommendation Survey*, students created a survey for better predictions. What kind of data should they collect?

• Shoe prices

• Which shoes users wear in different weather or activities

• Store names

• Brand logos

In *Lesson 4: Shoe Recommendation Survey*, students studied survey results. Why are patterns in the data useful?

• They help predict what users might like next time

• They replace human designers

• They slow the app down

• They stop the app from collecting data

In *Lesson 4: Ultimate Shoe Recommender*, students saw the final version of the app. How does this app make shoe decisions?

• With prewritten rules only

• With random guessing

• With machine learning that finds patterns in data

• With shoe size only

In *Lesson 4: Ultimate Shoe Recommender*, students discussed how computer models think. What strategy do computer models use to make decisions?

• They find and use patterns in data

• They rely only on human rules

• They guess randomly

• They ignore data

In *Lesson 4: All Activities*, students compared human-written rules with machine learning. Why is machine learning more powerful?

• It can adapt automatically to new data

• It never makes mistakes

• It ignores feedback

• It runs without any data

In *Lesson 4: All Activities*, students learned about collecting good data. What makes a dataset more useful for training a model?

• Having many diverse responses

• Using only one person’s answers

• Guessing values

• Copying random numbers