Choose the objective first on the How to Train Models track. The objective is the decision plus the cost of being wrong. Training needs a loss that points at that decision. If you care about missing fraud, accuracy is the wrong target.
This lesson assumes you already worked through What training actually changes.
The idea in practice
Write false-alarm cost and miss cost before you pick a model family.
A concrete check
goal = {
'track': 'How to Train Models',
'lesson': 'Choose the objective first',
}
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
Picking a model from a leaderboard that used a different objective. 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
Write one sentence: we would rather make this mistake than that one.
Self-check
- Say Choose the objective first 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.