Supervised Learning: Hadrien Lacroix
Supervised Learning: Hadrien Lacroix
Supervised Learning: Hadrien Lacroix
M A C H I N E L E A R N I N G F O R E V E R YO N E
Hadrien Lacroix
Content Developer at DataCamp
Modeling
Hadrien Lacroix
Content Developer at DataCamp
Supervised learning
...
Hadrien Lacroix
Content Developer at DataCamp
Evaluate step
Model memorized training data and can't generalize learnings to new data
48 / 50 = 96%
28 correctly classified
= 93.33%
30 total points
Misses majority of fraudulent transactions
1 https://www. ickr.com/photos/59632563@N04/6104068209
true positives
Sensitivity = = 1/3 = 33.33%
true positives + false negatives
Rather mark legitimate transactions as suspicious than authorize fraudulent transactions
Rather send spam to inbox than send real emails to the spam folder
Error = distance between point (actual value) and line (predicted value)
1 https://www. ickr.com/photos/micahdowty/8540188997
Hadrien Lacroix
Content Developer at DataCamp
Machine learning work ow
Hyperparameter tuning
Ensemble methods
degree
gamma
shrinking
coef0
tol
...