Joint ADASYN and AdaBoostSVM for Imbalanced Learining

For a balanced data set support vector machine (SVM) generally has good performance and generalization, but SVMs can only produce suboptimal results with imbalanced data sets. In this paper, a AS-AdaBoostSVM algorithm was proposed based on SVM.First,by using ADASYN sampling, the density of small class sample in the border area was improved. Then, the decision classifiers was achieved by using RBFSVM as the weak classifiers in AdaBoost algorithm. By comparing the test results on a variety of unbalanced data sets with ADASYN, AdaBoostSVM, SMOTEBoost, it shows that the proposed algorithm is effective and robust.