Synthetic Oversampling with the Majority Class: A New Perspective on Handling Extreme Imbalance.
Shiven SharmaColin BellingerBartosz KrawczykOsmar R. ZaïaneNathalie JapkowiczPublished in: ICDM (2018)
Keyphrases
- class imbalance
- majority class
- minority class
- class distribution
- imbalanced datasets
- active learning
- imbalanced data
- cost sensitive
- cost sensitive learning
- classification error
- high dimensionality
- misclassification costs
- training set
- support vector machine
- nearest neighbour
- concept drift
- sampling methods
- decision boundary
- feature selection
- original data
- attribute selection
- feature extraction
- training dataset
- error rate
- high dimensional data
- multi class