Ensemble imbalance classification: Using data preprocessing, clustering algorithm and genetic algorithm

One of the most interesting and important issues in the machine learning and data mining research areas is high accuracy classification. Imbalance data is a great challenge. The imbalance data is a kind of situation when the number of one data member class is significantly smaller than the other class. In the recent years this issue has got more attention among many researchers all over the world. In this paper we are going to propose a new algorithm for dealing and classifying the imbalance data. In the first part of the proposed method the SMOTE (Synthetic Minority Oversampling TEchnique) oversampling preprocessing is done for increasing the numbers of minority members of the dataset in order to emphasize them, then the algorithm is run on the 10 binary classes, imbalance KEEL datasets. The experimental results show that the proposed ensemble learning algorithm has better results than some well-known algorithms such as SMOTEBagging and SMOTEBoosting in imbalance data.