Separate a Feature from a Training Label
Distinguish input information, known teaching outcome and model output before evaluating a case.
About 18 minutes, plus any extended practice
Open lesson 1Evaluate a Simple Classification Model
Use eight held-out cases with six correct predictions. Explain the accuracy and classify a reusable prediction whose label is not reusable. State one limitation.
Before you begin
- Compare categories and calculate simple percentages.
Choose by skill rather than age alone. Read with an adult when useful, revisit a lesson, or explore another grade.
Follow the lesson sequence
Count Correct Predictions on Held-Out Cases
Divide correct predictions by all evaluated cases when calculating this test-set accuracy.
About 18 minutes, plus any extended practice
Open lesson 2Distinguish Two Types of Prediction Error
Compare the predicted category with the supplied actual category.
About 18 minutes, plus any extended practice
Open lesson 3Keep Training Results Separate from Test Evidence
Use an untouched evaluation set for the stated generalization check and disclose its scope.
About 18 minutes, plus any extended practice
Open lesson 4Review and transfer
After the lessons, try 4 new review cases and a practical task. Each answer has an explanation and a link back to the related lesson.
Open the unit reviewGuest answers are temporary. Keep your own paper or document; this unit does not certify completion or record a school grade.
Topic references
- 2026 CSTA PK–12 Computer Science Standards: topic reference — Algorithms & Design; Data & Analysis
These references informed the topic selection. They do not certify complete standards alignment.