A New Over-Sampling Method Based on Cluster Ensembles

Abstract

Most of the traditional classification methods behave undesirable, particularly producing poor predictive accuracy for the minority class of the imbalanced data from real world applications. This paper proposes a novel over-sampling strategy to handle imbalanced data based on cluster ensembles, named CE-SMOTE, which aims to provide a better training platform by introducing clustering consistency index to find out the cluster boundary minority samples and then over-sampling these minority samples to augment the original data set. Experiments carried out on some imbalanced public data sets show that the proposed method is effective and feasible to deal with the imbalanced data sets, and can produce high predictions for both minority and majority classes.