Exploratory Undersampling for Class-Imbalance Learning

• Published in: IEEE transactions on systems, man and cybernetics. Part B, Cybernetics Vol. 39; no. 2; pp. 539 - 550
• Main Authors: Liu, Xu-Ying, Wu, Jianxin, Zhou, Zhi-Hua
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.04.2009
• Subjects: Algorithms; Balancing; Class-imbalance learning; Classifiers; Costs; Credit cards; Cybernetics; Data mining; Dealing; ensemble learning; Error analysis; Laboratories; Learning; Learning systems; Machine learning; Research and development; Sampling methods; Training; Trains; undersampling; ensemble learning; Class-imbalance learning; machine learning; data mining; undersampling
• ISSN: 1083-4419; 1941-0492; 1941-0492
• DOI: 10.1109/TSMCB.2008.2007853

Undersampling is a popular method in dealing with class-imbalance problems, which uses only a subset of the majority class and thus is very efficient. The main deficiency is that many majority class examples are ignored. We propose two algorithms to overcome this deficiency. EasyEnsemble samples several subsets from the majority class, trains a learner using each of them, and combines the outputs of those learners. BalanceCascade trains the learners sequentially, where in each step, the majority class examples that are correctly classified by the current trained learners are removed from further consideration. Experimental results show that both methods have higher Area Under the ROC Curve, F-measure, and G-mean values than many existing class-imbalance learning methods. Moreover, they have approximately the same training time as that of undersampling when the same number of weak classifiers is used, which is significantly faster than other methods.