Doing the Work Section 018
Scoping an ML Project
Deciding what to build, whether machine learning is even the right answer, and how you will know it worked.
11 of 11 lessons published Three reading levels on every lesson
Lessons in order
Work top to bottom. Each lesson assumes the one above it.
- When rules beat machine learning
- Turning a vague request into a prediction task
- Choosing the label
- Can this even be learned?
- Choosing the metric that matches the decision
- Designing for a human reviewer
- Write down the constraints before choosing a model
- Check the data exists before promising the model
- The one-page ML project brief
- Getting knowledge out of a domain expert
- Explaining a model to the person who decides