Issues in Mining Imbalanced Data Sets - A Review Paper

ID:39888400

大小:110.52 KB

页数:7页

时间:2019-07-14

Issues in Mining Imbalanced Data Sets - A Review Paper_第1页
Issues in Mining Imbalanced Data Sets - A Review Paper_第2页
Issues in Mining Imbalanced Data Sets - A Review Paper_第3页
Issues in Mining Imbalanced Data Sets - A Review Paper_第4页
Issues in Mining Imbalanced Data Sets - A Review Paper_第5页
资源描述:

《Issues in Mining Imbalanced Data Sets - A Review Paper》由会员上传分享,免费在线阅读,更多相关内容在学术论文-天天文库

1、IssuesinMiningImbalancedDataSets-AReviewPaperSofiaVisaAncaRalescuECECSDepartmentECECSDepartmentML0030ML0030UniversityofCincinnatiUniversityofCincinnatiCincinnati,OH45221,USACincinnati,OH45221,USAsvisa@ececs.uc.eduAnca.Ralescu@uc.eduAbstractExample2(TrainingandtestingdistributionarerarelyThis

2、papertracessomeoftherecentprogressinthefieldofthesame)Classdistributionisanimportantissueforlearn-learningofimbalanceddata.Itreviewsapproachesadopteding,ingeneral.Thetrainingdatamightbeimbalancedbutforthisproblemanditidentifieschallengesandpointsoutthetestingmightnotandtheotherwayaround.Howev

3、er,futuredirectionsinthisrelativelynewfield.experimentalstudiesshowthatabalancedclassdistributionisnotthebestforlearning(Weiss&Provost2003),(Visa&IntroductionRalescu2005)andtheopenquestionforfurtherresearchis:WhatisthebestclassdistributionforlearningagivenLearningwithimbalancedclassdistribut

4、ionsaddressesthetask?casewhen,foratwo-classclassificationproblem,thetrain-ingdataforoneclass(majority)greatlyoutnumberstheExample3(Inapplications,errorcostaredifferent)Inotherclass(minority).Recently,machinelearningcommu-applicationstheerrorcostaredifferent:consideracancernityacknowledgedtha

5、tthecurrentlearningmethods(e.g.versusnon-cancer,fraudversusvalidaction,systemOKver-C4.5,NN)performpoorlyinapplicationsdealingwithim-sussystemfailuresituation.Iftheerrorcostsandclassdis-balanceddatasets(IDS).Ontheotherhand,itwasobservedtributionareknownthecorrectthresholdcanbecomputedthatinm

6、anyrealworlddomainsavailabledatasetsareim-easily.Butthedifficultyisthaterrorcostsarehardtoassessbalanced.Intheliterature,theIDSproblemisalsoknownevenbythehumanexpertsinthefield,andtherefore,theseasdealingwithrareclasses,orwithskeweddata.costsarerarelyknown.Further,itisimportanttomentionThepoo

7、rperformanceoftheclassifiersproducedbythethat,whentheerrorscomingfromdifferentclasseshavedif-standardmachinelearningalgorithmsonIDSismainlydueferentbutunknowncost,classifiershaveproblemsevenfortothefollowingfactors:thebalanceddata.Inordertogiveacomprehensi

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
正文描述:

《Issues in Mining Imbalanced Data Sets - A Review Paper》由会员上传分享,免费在线阅读,更多相关内容在学术论文-天天文库

1、IssuesinMiningImbalancedDataSets-AReviewPaperSofiaVisaAncaRalescuECECSDepartmentECECSDepartmentML0030ML0030UniversityofCincinnatiUniversityofCincinnatiCincinnati,OH45221,USACincinnati,OH45221,USAsvisa@ececs.uc.eduAnca.Ralescu@uc.eduAbstractExample2(TrainingandtestingdistributionarerarelyThis

2、papertracessomeoftherecentprogressinthefieldofthesame)Classdistributionisanimportantissueforlearn-learningofimbalanceddata.Itreviewsapproachesadopteding,ingeneral.Thetrainingdatamightbeimbalancedbutforthisproblemanditidentifieschallengesandpointsoutthetestingmightnotandtheotherwayaround.Howev

3、er,futuredirectionsinthisrelativelynewfield.experimentalstudiesshowthatabalancedclassdistributionisnotthebestforlearning(Weiss&Provost2003),(Visa&IntroductionRalescu2005)andtheopenquestionforfurtherresearchis:WhatisthebestclassdistributionforlearningagivenLearningwithimbalancedclassdistribut

4、ionsaddressesthetask?casewhen,foratwo-classclassificationproblem,thetrain-ingdataforoneclass(majority)greatlyoutnumberstheExample3(Inapplications,errorcostaredifferent)Inotherclass(minority).Recently,machinelearningcommu-applicationstheerrorcostaredifferent:consideracancernityacknowledgedtha

5、tthecurrentlearningmethods(e.g.versusnon-cancer,fraudversusvalidaction,systemOKver-C4.5,NN)performpoorlyinapplicationsdealingwithim-sussystemfailuresituation.Iftheerrorcostsandclassdis-balanceddatasets(IDS).Ontheotherhand,itwasobservedtributionareknownthecorrectthresholdcanbecomputedthatinm

6、anyrealworlddomainsavailabledatasetsareim-easily.Butthedifficultyisthaterrorcostsarehardtoassessbalanced.Intheliterature,theIDSproblemisalsoknownevenbythehumanexpertsinthefield,andtherefore,theseasdealingwithrareclasses,orwithskeweddata.costsarerarelyknown.Further,itisimportanttomentionThepoo

7、rperformanceoftheclassifiersproducedbythethat,whentheerrorscomingfromdifferentclasseshavedif-standardmachinelearningalgorithmsonIDSismainlydueferentbutunknowncost,classifiershaveproblemsevenfortothefollowingfactors:thebalanceddata.Inordertogiveacomprehensi

显示全部收起
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。
关闭