一种针对类别不平衡的代价敏感集成算法  

A cost sensitive integration algorithm for class imbalance

作　　者：谭浩[1] 田爱奎[1] 吴志勇[1] TAN Hao;TIAN Ai kui;WU Zhi yong(School of Computcr Science and Technology,Shandong University of Technology,Zibo 255019,China)

机构地区：[1]山东理工大学计算机科学与技术学院,山东淄博255049

出　　处：《山东理工大学学报（自然科学版）》2018年第6期63-66,共4页Journal of Shandong University of Technology:Natural Science Edition

摘　　要：现实世界中的数据挖掘经常涉及从类别分布不平衡的数据集学习,少数类的数量相比于其他类较少.从包含少数类的数据集中学习,通常会产生偏向于多数类的预测分类器,但对少数类的预测精度较差.针对少数类学习提出一种新的集成算法Cost-SMOTEBoost,该算法是SMOTE算法和AdaCost算法的结合.通过实验表明,Cost-SMOTEBoost算法在不降低精确率的情况下提高了召回率,从而提高了在分布不平衡数据集上的表现.Many real world data mining applications involve learning from imbalanced data sets,where the particular events of interest may be very fewer when compared to the other classes.Learning from data sets that contain rare events usually produces biased classifiers that have a higher predictive accuracy over the majority class,but poorer predictive accuracy over the minority class of interest.This paper presents a novel approach Cost-SMOTEBoost for learning from rare classes,based on the combination of the SMOTE algorithm and the AdaCost algorithm.Experiments show that Cost-SMOTEBoost can improve recall without reducing the precision.The algorithm does better on the imbalanced dataset.

关 键 词：类别不平衡 集成 代价敏感 过抽取 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]