Baselines on the AI Learning track. A baseline is a simple method you must beat: predict the average, predict the majority class, or a small linear model. If you cannot beat it, the complex model is not earning its cost.
This lesson assumes you already worked through Metrics that match the decision.
The idea in practice
Implement the baseline first and score it on the same validation split. Put the number in the report before any deep model.
A concrete check
goal = {
'track': 'AI Learning',
'lesson': 'Baselines',
}
checks = [
'input available at decision time',
'score matches the real decision',
'failure case written down',
]
print(goal['lesson'])
for item in checks:
print('-', item)
Run the sketch locally if you have Python. The printout is a reminder of the checks, not a trained model. Replace the strings with the real inputs from your own example before you treat it as a design.
What usually goes wrong
Showing only the neural net score with nothing to compare. When this happens, stop adding parameters or tools. Fix the check, the data, or the permission, then run the same example again.
What to write down
- The input you are allowed to use at decision time.
- The output and the score or pass rule.
- One failure you will test on purpose.
- What you will not claim the system can do.
Practice
Name the baseline you would use for 'will this user return next week'.
Self-check
- Say Baselines in one sentence that mentions an input and an output.
- Name the failure mode in this lesson and the check that would catch it.
Done when: you can explain this lesson without the page open, and you have a written failure case.