GMDH-Based Outlier Detection Model in Classification Problems  

作　　者：XIE Ling JIA Yanlin XIAO Jin GU Xin HUANG Jing 

机构地区：[1]School of Medical Information Engineering,Zunyi Medical University,Zunyi 563006,China [2]Business School,Sichuan University,Chengdu 610064,China [3]Soft Science Institute,Sichuan University,Chengdu 610064,China [4]School of Public Administration,Sichuan University,Chengdu 610064,China

出　　处：《Journal of Systems Science & Complexity》2020年第5期1516-1532,共17页系统科学与复杂性学报（英文版）

基　　金：partly supported by the Major Project of the National Social Science Foundation of China under Grant No.18VZL006;the National Natural Science Foundation of China under Grant Nos.71571126and 71974139;the Excellent Youth Foundation of Sichuan Province under Grant No.20JCQN0225;the Tianfu Ten-thousand Talents Program of Sichuan Province;the Excellent Youth Foundation of Sichuan University under Grant No.sksyl201709;the Leading Cultivation Talents Program of Sichuan University;the Teacher and Student Joint Innovation Project of Business School of Sichuan University under Grant No.LH2018011;the2018 Special Project for Cultivation and Innovation of New Academic;Qian Platform Talent under Grant No.5772-012。

摘　　要：In many practical classification problems,datasets would have a portion of outliers,which could greatly affect the performance of the constructed models.In order to address this issue,we apply the group method of data handin neural network in outlier detection.This study builds a GMDH-based outlier detectio model.This model first implements feature selection in the training set L using GMDH neural network.Then a new training set L can be obtained by mapping the selected key feature subset.Next,a linear regression model can be constructed in the set L by ordinary least squares estimation.Further,it eliminates a sample from the set L randomly every time,and then rebuilds a linear regression model.Finally,outlier detection is realized by calculating Cook’s distance for each sample.Four different customer classification datasets are used to conduct experiments.Results show that GOD model can effectively eliminate outliers,and compared with the five existing outlier detection models,it generally performs significantly better.This indicates that eliminating outliers can effectively enhance classification accuracy of the trained classification model.

关 键 词：Classification problem Cook’s distance feature selection GMDH outlier detection 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论] TP18[自动化与计算机技术—计算机科学与技术]