Chapter 1: Classical ML
Welcome to Classical ML: a model from start to finish
Many people think machine learning starts when you pick a model. Real work and real interviews start earlier, with the question, and they end with an honest score. In this lesson, you do the whole job once, roughly, on one streaming app.
What you will learn
- Name the five steps of machine learning work
- Tell a learn-from-examples problem from a rule or lookup
- Know what each part of the chapter answers
Key terms
- feature
- An input column the model uses, such as hours listened.
- label
- The answer the model must predict for each past example.
- training set
- The examples the model learns from.
- validation set
- Examples kept aside to choose between versions of the model.
- test set
- Examples kept unseen for one final, honest score.
Prerequisites
Take Getting the job first. It comes right before this lesson in the course.
What comes next
Step one was choosing what to predict. Next, you do it properly.
Next lesson: Framing: what to predict, for whom, when, and what to beat
More lessons in this part
- Framing: what to predict, for whom, when, and what to beat 24 min
- Fitting a line: what 'best fit' means and how to read the slope 20 min
- The exact best line: two equations, and MAE 20 min
- From a line to a probability: the sigmoid 7 min
- Training logistic regression: log loss, its gradient, and why not squared error 7 min
- Thresholds, precision and recall: the cut-off is a product decision 16 min
- Honest splits and leakage: random, group and time-based 18 min
Take the lesson
Short cards, one idea at a time, with quick checks as you go.