Skip to content
PlayOwl

Computers & Digital Literacy · Grade 9

Model Evaluation and Error Analysis

Learners evaluate a fictional leak-detection model the way practitioners do: they build confusion matrices and compute accuracy, precision, recall, specificity and F1 with the real formulas, compare the model with a majority-class baseline, and measure regression error with mean absolute error. They then choose a decision threshold from the costs of each error type and break errors down by subgroup and by error type to recommend next steps.

  • 5 lessons
  • About 125 minutes
  • Evaluation check: 10 questions
  • Ways to answer: choose an answer, trace code, highlight a text, match pairs, type a number and sort into groups
Try it now (no account) One of the five free starter courses Open in PlayOwl

What learners will discover

  • Build a confusion matrix from predictions and compute accuracy, precision, recall and specificity.
  • Compute F1 and compare a model with a majority-class baseline, explaining why accuracy misleads when one class is rare.
  • Compute mean absolute error for a regression model and compare it with a simple baseline.
  • Explain how moving a decision threshold trades precision against recall, and choose a threshold or metric from the costs of each error type.
  • Analyze errors by subgroup and by error type, and recommend evidence-based next steps.

Lessons

  1. The confusion matrix and four metrics 8 steps5 practiceabout 30 min
  2. F1 and the majority-class baseline 6 steps4 practiceabout 24 min
  3. Measuring regression error 5 steps3 practiceabout 20 min
  4. Thresholds and the cost of errors 6 steps4 practiceabout 26 min
  5. Error analysis by subgroup and error type 6 steps3 practiceabout 25 min
  6. Evaluation check 10 questions at the end

Keep exploring

More 9th grade computer skills

Guide for grown-ups