A novel ensemble method for classification in imbalanced datasets using split balancing technique based on instance hardness (sBal_IH)

Classification tasks in datasets that suffer from high class imbalance pose challenge to machine learning algorithms and such datasets are prevalent in many real-world domains and applications. In machine learning research, ensemble methods for classification tasks in imbalanced datasets have attracted a lot of attention due to their ability to improve classification performance. However, these methods are still prone to the negative effects of noise in the training sets. Furthermore, many of them alter the original class distribution to create a sort of balance in the datasets through over-sampling or undersampling techniques, which can lead to overfitting or discarding useful data, respectively, and thus may still hamper performance. In this work, we propose a novel ensemble method for classification that creates an arbitrary number of balanced splits (sBal) of data generated based on Instance Hardness as a weighting mechanism for creating balanced bags. Each of the generated bags will contain all the minority instances, and a mixture of majority instances with varying degrees of hardness (easy, normal, and hard), and we call this approach sBal_IH technique. This will enable base learners to train on different balanced bags comprising varied characteristics of the training data. We evaluated the performance of our proposed method on a total of 100 datasets that include 30 synthetic datasets with controlled levels of noise, 29 balanced and 41 imbalanced real-world datasets, and compared its performance with both traditional ensemble methods (Bagging, Wagging Random Forest, and AdaBoost), and those specialized for class imbalanced problems (Balanced Bagging, Balanced Random forest, RUSBoost, and Easy Ensemble). The results reveal that our proposed method brings a substantial improvement in classification performance relevant to the compared methods. For statistical significance analysis, we conducted Friedman’s nonparametric statistical test with Bergman post hoc test. The analysis shows that our method performs significantly better than the compared traditional and specialized ensemble methods for imbalanced problems across many datasets.