Handling Imbalanced Datasets — Roadmap Step & Resources
Oversampling, undersampling and SMOTE for datasets with rare positive classes
- Level: advanced
- Estimated time: 1 days
- Roadmap: Machine Learning
Before this step
Interview questions
- What's the risk of naively oversampling the minority class before splitting into train/test?
Study resources
- SMOTE Explained (Article) — The official imbalanced-learn documentation for SMOTE oversampling.
- Handling Imbalanced Datasets Explained (Video) — A practical walkthrough of oversampling, undersampling and class weighting.
Part of
- Feature Engineering & Selection — section
- Machine Learning roadmap — the full learning path