Handling Imbalanced Data — Roadmap Step & Resources
Techniques for when the outcome you care about is rare
- Level: advanced
- Estimated time: 1 days
- Roadmap: Data Science
Before this step
Interview questions
- Why can oversampling before splitting into train/test quietly leak information?
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 & Data Preparation for Modeling — section
- Data Science roadmap — the full learning path