- resampling
- over sampling
- random over sampling
- generate synthetic examples: SMOTE(synthetic minority oversampling technique) by a neareast neighbors approach
- under sampling
- random under sampling
- Tomek links
- model-level methods
- use class-banlaned loss(类别不平衡损失函数.pdf)
- 加权交叉熵
- Focal Loss
- CB Loss
- select appropriate algorithms
- tree-based models
- Logistic regression: adjust the probability threshold
- combine multiple algorithms
- under-sampling + ensemble
- under-sampling + class-banlaned loss
- under-sampling + ensemble
- use class-banlaned loss(类别不平衡损失函数.pdf)
- evaluation metrics
- Precision, recall, F1
- Precision-Recall curve
- AUC of the ROC curve