FALSE FINANCIAL STATEMENTS CHARACTERISTICS OF CHINA’S LISTED COMPANIES AND CART DETECTING APPROACH

FALSE FINANCIAL STATEMENTS CHARACTERISTICS OF CHINA’S LISTED COMPANIES AND CART DETECTING APPROACH

ID:39714521

大小:270.50 KB

页数:22页

时间:2019-07-09

FALSE FINANCIAL STATEMENTS CHARACTERISTICS OF CHINA’S LISTED COMPANIES AND CART DETECTING APPROACH_第1页
FALSE FINANCIAL STATEMENTS CHARACTERISTICS OF CHINA’S LISTED COMPANIES AND CART DETECTING APPROACH_第2页
FALSE FINANCIAL STATEMENTS CHARACTERISTICS OF CHINA’S LISTED COMPANIES AND CART DETECTING APPROACH_第3页
FALSE FINANCIAL STATEMENTS CHARACTERISTICS OF CHINA’S LISTED COMPANIES AND CART DETECTING APPROACH_第4页
FALSE FINANCIAL STATEMENTS CHARACTERISTICS OF CHINA’S LISTED COMPANIES AND CART DETECTING APPROACH_第5页
资源描述:

《FALSE FINANCIAL STATEMENTS CHARACTERISTICS OF CHINA’S LISTED COMPANIES AND CART DETECTING APPROACH》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、June5,200812:27WSPC/173-IJITDM00295InternationalJournalofInformationTechnology&DecisionMakingVol.7,No.2(2008)339–359cWorldScientificPublishingCompanyFALSEFINANCIALSTATEMENTS:CHARACTERISTICSOFCHINA’SLISTEDCOMPANIESANDCARTDETECTINGAPPROACH∗BELINNABAICreditDepartment,AgricultureBankofChina(HKBranch)2

2、3/F,Tower1,AdmiraltyCentre,HongKongbailinghk@gmail.comJEROMEYENDepartmentofFinanceTheHongKongUniversityofScienceandTechnologyClearWaterBay,Kowloon,HongKongrisksolution@gmail.comXIAOGUANGYANGAcademyofMathematicsandSystemsScienceChineseAcademyofSciences,Beijing,100080,Chinaxgyang@iss.ac.cnFalseFinan

3、cialStatements(FFS)havelongbeenaseriousprobleminChinaandotherAsiancountries,whichsignificantlydampentheconfidenceoftheinvestors.Regardlessoflistedcompaniesornon-listedcompanies,thepercentageoffinancialstatementsthatcontainedfalseinformationisquitehigh,whichisoneofthemajorreasonswhyChinastockmarketsmo

4、vedintheoppositedirectiontowardsitswonderfuleconomicgrowthoverthepastfewyears.Theobjectiveofthisresearchistointroduceonestatisticaltech-nique—ClassificationandRegressionTree(CART),toidentifyandpredicttheimpactsofFFS.Wesurveyfinancialstatementsmanipulationtricks,FFSindicatorsandFFSdetectiontechniques

5、frombothChinaandinternationalperspective,andfurtherlookintotenlistedcompanieswithknownFFShistoryinChina;combiningthesefindings,weproposekeyindicatorstoworkwithCART.Ouranalysisincludes24falsefinancialreports,and124non-falsefinancialreports.WeuseCARTtodeveloptwoFFSdetectingmodels:CARTwithoutindustryben

6、chmarkandCARTwithindustrybenchmark.Forsupportingcomparison,wealsobuildaLogitregressionwhichisacommonlyusedtechniqueinFFSdetecting.WefindthatCARTiseffectiveindistinguishingFFSfromnon-FFS.BothCARTmodelsachievebetteraccuracyinidentifyingfraudcasesandmakingpredictionsthanLogitregressiondoes,andCARTwithi

7、ndustrybenchmarkisslightlybetterthanCARTwithoutbenchmark,butitdoesnotalwayshavesuperiorperformance.OurCARTmodelalsotriestocapture∗TheresearchissupportedbyNSFC(Nos:70425004,700221001).339June5,200812:27WSPC/173-IJ

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
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。