Activity: Create an Algorithm Candidate Plan

Estimated active time: 45-70 minutes

Scenario

A fictional learning platform wants to predict whether a learner may need extra support in the next two weeks. The data is synthetic and not from real learners.

You have:

• course progress percentage;
• recent practice activity;
• number of assessment attempts;
• days since last activity;
• course level;
• support-ticket count;
• prior course completion;
• a binary label showing whether support was needed later.

Use:

• data/learner_success_algorithm_v1.csv
• notebooks/module-01-planning-notebook.ipynb
• learner-resources/algorithm-comparison-report-template.md

Task

Create an algorithm candidate plan before fitting any model.

Required sections

1. Problem statement.
2. Data shape and likely preprocessing needs.
3. Decision and error-cost note.
4. Baseline ladder with four steps.
5. Three candidate model families to try.
6. Two model families or techniques to reject for now.
7. Metric and validation plan.
8. One limitation note.

Rules

• Include a dummy baseline.
• Include at least one simple model.
• Do not choose a complex model only because it is popular.
• Do not use the test set for model selection.
• Do not claim the model is ready for real learner decisions.

Output

Use learner-resources/algorithm-comparison-report-template.md or your own one-page memo with the same sections.