基于LOGISTIC回归的上市公司财务欺诈检测研究（可复制毕业论文）.pdf

河北工业大学硕士学位论文
基于 Logistic 回归的上市公司财务欺诈检测研究

摘要

中国证券市场自开市以来,财务欺诈案件层出不穷,在很大程度上打击了投资者的投
资信心,破坏了资本市场的健康发展;近期,股市持续低迷、投资者大都采取观望态度,
这些都加大了上市公司财务欺诈的动机。如何通过简单易行的方法检测上市公司的财务欺
诈行为,成为了广大投资者、证券监管部门、注册会计师等利益相关群体极为关注的问题。
本文在分析上市公司公开财务数据的基础上建立检测模型。在中国,部分欺诈行为能
借助审计人员出具的审计报告识别。本文样本总共涉及 490 份财务报告,其中包括 245 份
欺诈财务报告和 245 份非欺诈报告;选择了 27 个财务指标作为分析欺诈财物报告的潜在
因素,运用拟合单变量和多因素统计技术 Logistic 回归分析建立检测模型,模型可以精
确的对总体样本进行分类,准确率超过 78%,结果证实了模型可以有效的发现欺诈性财务
报告,可以辅助审计人员分析虚假财务报告。

关键词:上市公司,财务欺诈报告,Logistic 回归
i
河北工业大学硕士学位论文
RESEARCH ON FINANCIAL FRAUD DETECTION OF LISTED
COMPANIES BASED ON LOGISTIC REGRESSION

ABSTRACT

Since the opening of China’s stock market, we observe a frequent break out of the financial
frauds. In some extents, it has shocked the investors’ confidence and has held back the healthy
development of China’s capital market. Recently the stock market has kept on depression, most
investors are entertaining the attitude of ride the above has raised the motivation of
accounting fraud. How to detect the financial statement distortions easily has raised significant
attention from investors, regulators and auditors, etc.
This dissertation examines published data to develop a model for detecting factors associated
with fraudulent financial statements (FFS). Most fraudulent financial statements in china can be
identified on the basis of the quantity and content of the qualification in the reports filed by the
auditors on the accounts. A sample of a total of 490 statements includes 245 with FFS and 245
non-FFS. Twenty seven financial variables are selected for examination as potential predictors of
FFS. Univariate and Multivariate statistical techniques such as logistic regression are used to
develop a model to detect factors associated with FFS. The model is accurate in classifying the
total sample correctly with accuracy rates exceeding 78 percent. The result therefore demonstrate
that the modelsfunction effectively in