Under-sampling by algorithm with performance guaranteed for class-imbalance problem

Abstract

Class-imbalance problem is the problem that the number, or data, in the majority class is much more than in the minority class. Traditional classifiers cannot sort out this problem because they focus on the data in the majority class than on the data in the minority class, and then they predict some upcoming data as the data in the majority class. Under-sampling is an efficient way to handle this problem because this method selects the representatives of the data in the majority class. For this reason, under-sampling occupies shorter training period than over-sampling. The only problem with the under-sampling method is that a representative selection, in all probability, throws away important information in a majority class. To overcome this problem, we propose a cluster-based under-sampling method. We use a clustering algorithm that is performance guaranteed, named k-centers algorithm, which clusters the data in the majority class and selects a number of representative data in many proportions, and then combines them with all the data in the minority class as a training set. In this paper, we compare our approach with k-means on five datasets from UCI with two classifiers: 5-nearest neighbors and c4.5 decision tree. The performance is measured by Precision, Recall, F-measure, and Accuracy. The experimental results show that our approach has higher measurements than the k-means approach, except Precision where both the approaches have the same rate.