An imbalanced learning method by combining SMOTE with Center Offset Factor

• Published in: Applied soft computing 2022-05, Vol.120, p.108618, Article 108618
• Main Authors: Meng, Dongxia, Li, Yujian
• Format: Article
• Language: English
• Subjects: Center shift; Imbalanced datasets; k nearest neighbors; Oversampling; SMOTE
• ISSN: 1568-4946; 1872-9681
• DOI: 10.1016/j.asoc.2022.108618

SMOTE is a well-known oversampling method for learning on imbalanced datasets. However, it has the risk of introducing noisy instances and overfitting problems. In order to improve its performance, this paper proposes an oversampling method called SMOTE-COF, which is an improvement of SMOTE based on center offset factor. The SMOTE-COF method first removes noisy samples, then computes center offset factor to select sparsely distributed minority class samples. Furthermore, these samples are used to generate new minority class samples with other minority class instances distributed in the same sub-cluster by SMOTE. Comparative experiments on one simulated dataset and fourteen UCI datasets provide evidence that the SMOTE-COF can effectively reduce noisy samples, generate better minority classes, and improve classification performance for imbalanced datasets. •SSMOTE-COF is an improvement of SMOTE based on center offset factor.•SMOTE-COF computes center offset factor to select sparsely distributed minority class samples.•Sparse samples generate new samples with other minority class instances distributed in the same sub-cluster by SMOTE.•SMOTE-COF can generate better minority classes, and improve classification performance for imbalanced datasets.