An empirical study on preprocessing high-dimensional class-imbalanced data for classification

Computer Science

• Feature Selection 100%
• Imbalanced Data 100%
• Classifier 60%
• Sampling Data 60%
• Classification Method 20%
• Data Type 20%
• Data Mining 20%
• Majority Class 20%
• Class Imbalance 20%

Mathematics

• Sampling Data 100%
• Oversampling 66%
• Data Mining 33%
• Data Type 33%
• Classification Method 33%
• Majority Class 33%
• Direct Method 33%
• Curse of Dimensionality 33%
• Higher Dimensions 33%