摘要
针对虚假财务报告的特点，设计了一种基于BP（反向传播）神经网络的虚假财务报告识别模型。根据1999-2002年的年度审计报告意见。从上市公司中，选择确定了44家虚假财务报告样本，并按照一定的标准选择了44家真实财务报告样本，这88个样本构成训练数据集。类似地，从2003-2006年的上市公司中，选择了73家虚假财务报告样本和99家真实财务报告样本，这172个样本构成测试数据集。10个财务指标被选择为识别变量，使用训练数据集对BP神经网络模型进行训练，并将训练后的模型对测试数据集进行测试，取得了较好的实验结果。
Considering the characteristics of fraudulent financial statements（FFS）, this paper designs a FFS detection model based on BP neural network. To carry out the experiment, we choose 44 FFS according to the auditing reports and 44 true financial statements according to some specific standards during 1999-2002 as training data set. Similarly, 73 FFS and 99 true financial statements during 2003-2006 are chosen as testing data set. Ten financial ratios are chosen as detection variables. We train the model by using training data set and apply the trained model to the testing data set, good experimental results are obtained.
出处
《系统工程》
CSCD
北大核心
2009年第10期70-75,共6页
Systems Engineering
关键词
虚假财务报告
识别
BP神经网络
识别变量
Fraudulent Financial Statement
Detection
BP Neural Network
Detection Variable
