CGMOS: Certainty Guided Minority OverSampling
This addresses the challenge of reduced classification performance in imbalanced datasets for machine learning practitioners, but it is an incremental improvement as it builds on the SMOTE algorithm.
The paper tackles the problem of imbalanced datasets by proposing CGMOS, a novel extension to SMOTE with a theoretical guarantee for improved classification performance, and experimental results on 30 real-world datasets show it outperforms existing algorithms with 6 different classifiers.
Handling imbalanced datasets is a challenging problem that if not treated correctly results in reduced classification performance. Imbalanced datasets are commonly handled using minority oversampling, whereas the SMOTE algorithm is a successful oversampling algorithm with numerous extensions. SMOTE extensions do not have a theoretical guarantee during training to work better than SMOTE and in many instances their performance is data dependent. In this paper we propose a novel extension to the SMOTE algorithm with a theoretical guarantee for improved classification performance. The proposed approach considers the classification performance of both the majority and minority classes. In the proposed approach CGMOS (Certainty Guided Minority OverSampling) new data points are added by considering certainty changes in the dataset. The paper provides a proof that the proposed algorithm is guaranteed to work better than SMOTE for training data. Further experimental results on 30 real-world datasets show that CGMOS works better than existing algorithms when using 6 different classifiers.