Survey of resampling techniques for improving classification performance in unbalanced datasets
This is a survey paper, providing an overview of existing methods for researchers and practitioners dealing with imbalanced data in classification tasks.
The paper reviews various resampling techniques from literature to address classification problems with imbalanced datasets, aiming to improve performance by enhancing recall on the minority class while maintaining precision on the majority class.
A number of classification problems need to deal with data imbalance between classes. Often it is desired to have a high recall on the minority class while maintaining a high precision on the majority class. In this paper, we review a number of resampling techniques proposed in literature to handle unbalanced datasets and study their effect on classification performance.