Capstone project

Time to put it all together. You'll take a real dataset and go end-to-end.

Your workflow

1. Frame the problem — what are you predicting, and why does it matter?
2. Explore & clean — understand the data, handle missing values.
3. Split — hold out a test set.
4. Train a baseline — start simple.
5. Evaluate — with the right metric, on unseen data.
6. Iterate — improve features and try a stronger model.
7. Interpret — what drives the prediction? Can you trust it?

Deliverable

A short notebook + a one-paragraph summary of what you built, how well it works, and what you'd do next. This is your first portfolio piece.

Congratulations — you've trained and evaluated a real ML model. That's the foundation everything else builds on.