Learning SVM with weighted maximum margin criterion for classification of imbalanced data
As a kernel-based method, whether the selected kernel matches the data determines the performance of support vector machine. Conventional support vector classifiers are not suitable to the imbalanced learning tasks since they tend to classify the instances to the majority class which is the less important class. In this paper, we propose a weighted maximum margin criterion to optimize the datadependent kernel, which makes the minority class more clustered in the induced feature space. We train support vector classification with the optimal kernel. The experimental results on nine benchmark data sets indicate the effectiveness of the proposed algorithm for imbalanced data classification problems.
Support vector machine Imbalanced data learning Kernel optimization Weighted maximum margin criterion
Zhuangyuan Zhao Ping Zhong Yaohong Zhao
College of Science, China Agricultural University, Beijing, 100083, PR China
国际会议
南昌
英文
1093-1099
2010-10-22（万方平台首次上网日期，不代表论文的发表时间）