ML Academy · Track 1 · Classical Machine Learning

Imbalanced data: threshold, weight, resampling

There are three standard fixes. We measured all three, and all three do the same thing, two of them while breaking the calibration.

4 steps 220 XP A free account is needed

Sources

Chawla, N. et al. 2002 · SMOTE: Synthetic Minority Over-sampling Technique · JAIR, 16
Provost, F. 2000 · Machine Learning from Imbalanced Data Sets 101 · AAAI Workshop
van den Goorbergh, R. et al. 2022 · The Harm of Class Imbalance Corrections for Risk Prediction Models · JAMIA, 29(9)

ML Academy · an interactive machine learning course that runs in your browser · All lessons