Under-sampling Method Research in Class-Imbalanced Data
ZHOU Jianwei
Abstract：Imbalanced dataset have a serious impact on the performance of classifiers in machine learning. This paper propos?es a under-sampling method based on Gaussian mixture model. The method exploits Gaussian mixture model to fit negative data, then gets under-sampling in proportion based on probability interval that is the distribution of data on each Gaussian component.The method achieves the class-imbalance by reducing the number of samples that belong to majority classes,at the same time,it main?tains the data distribution of majority classes.The experimental results on six groups UCI imbalanced dataset show the under-sam?pling method can effectively improve the classification performance on imbalanced dataset.
Keywords：imbalanced learningunder-samplinggaussian mixture modelmachine learning
Publication Date：2019-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：6( 2155-2160 )