Skip to course content
Free course

Machine Learning Foundations / Module 10

Module 10 activity

Activity: Complete the ML Foundations Capstone

Activity ID: ML-M10-A01 Estimated active time: 45-75 minutes

Goal

Produce the main Module 10 evidence: Capstone notebook, data card, model-quality report, responsible-use memo, reproducibility checklist, and reflection.

Inputs

  • data/module_10_capstone_v1.csv
  • data/data-dictionary.md
  • notebooks/module-10-worked.ipynb
  • notebooks/module-10-practice.ipynb

Instructions

  1. Frame the problem: decision, unit, target, and the cost of each error type.
  2. Write the dataset card, including the repeated unit and your split plan.
  3. Fit both baselines and at least one model, on a split grouped by the repeated unit.
  4. Report the comparison table and choose a threshold with a stated reason.
  5. Run the slice analysis from Module 9 and record any gap.
  6. Write the model card, including an out-of-scope section and next steps.

Quality checklist

  • [ ] Framing was written before any model was fitted.
  • [ ] The split is grouped by the repeated unit, and overlap is verified as zero.
  • [ ] Both baselines appear alongside the model.
  • [ ] The threshold choice cites the error-cost asymmetry.
  • [ ] The model card names where the model must not be used.
  • [ ] Next steps map to stated limitations.

Submission format

Submit the notebook output or worksheet table plus a 4-6 sentence explanation.

Safety note

Use only supplied fictional or synthetic data. Do not add or upload real learner data.