基于支持向量机对上市公司财务报表虚假性甄别  

The Discriminating of False Information in Financial Statements of Listed Companies Based on Support Vector Machine

作　　者：宋志坚[1] 邹昌文[1] 陈雨欣[1] 文旭东[1] 

机构地区：[1]重庆交通大学理学院,重庆400074

出　　处：《重庆工商大学学报（自然科学版）》2013年第9期24-28,共5页Journal of Chongqing Technology and Business University:Natural Science Edition

基　　金：重庆交通大学大学生创新创业训练项目(0618045)

摘　　要：分析了目前常见的财务报表虚假手段及常用识别方法,阐述了支持向量机方法财务用于报表虚假识别中的可行性及其特征属性的选择,对近年因财务虚假导致被证监会通报处罚的上市公司财务报表进行研究,结果表明该方法能较为理想的区分真实或虚假的财务报表。This paper analyzes the currently common method for making false financial statements and its common discriminating methods, elaborates the feasibility for using support vector machine method to discriminate false financial statements and to select its characteristic attributes, studies the financial statements of the listed companies exposed and punished by Securities Supervision Committee because of false financial information in recent years, and concludes that this method can relatively he ideal to discriminate real financial statements from false financial statements

关 键 词：财务报表 支持向量机 特征属性 

分 类 号：TP315[自动化与计算机技术—计算机软件与理论]