A NovelWeighted Ensemble Method to Overcome the Impact of Under-fitting and Over-fitting on the Classification Accuracy of the Imbalanced Data Sets

Abstract

In the data mining communal, imbalanced class dispersal data sets have established mounting consideration. The evolving field of data mining and information discovery seeks to establish precise and effective computational tools for the investigation of such data sets to excerpt innovative facts from statistics. Sampling methods re-balance the imbalanced data sets consequently improve the enactment of classifiers. For the classification of the imbalanced data sets, over-fitting and under-fitting are the two striking problems. In this study, a novel weighted ensemble method is anticipated to diminish the influence of over-fitting and under-fitting while classifying these kinds of data sets. Forty imbalanced data sets with varying imbalance ratios are engaged to conduct a comparative study. The enactment of the projected method is compared with four customary classifiers including decision tree(DT), k-nearest neighbor (KNN), support vector machines (SVM), and neural network (NN). This evaluation is completed with two over-sampling procedures, an adaptive synthetic sampling approach (ADASYN) and a synthetic minority over-sampling (SMOTE) technique. The projected scheme remained efficacious in diminishing the impact of over-fitting and under-fitting on the classification of these data sets.