← Path
Machine Learning Fundamentals · What Is Machine Learning? How to Frame a Problem (and When Not To)
0 XP- 1 current stop: learning
- 2 upcoming
- 3 upcoming
- 4 upcoming
- 5 upcoming
Finish after stop 5
Stop 1 of 5 · Bike shop: reading the speedometer
Trick to keep in mind+3 XP
Beat the lazy baseline first: if answering 'no' for everyone scores 95%, then 95% is zero skill.
A baseline is the score of the dumbest sensible strategy, such as always predicting the most common class. When one class makes up 95% of the data, that strategy is already right 95% of the time. A model only shows skill by clearly beating it, so look at how many of the rare cases it really catches.
Read it once, then a question tests whether the trick stuck.