论文部分内容阅读
本文以2001年至2008年间74家A股机械、设备、仪表业上市公司数据为研究对象,分别用多元判别、逻辑回归、BP神经网络和支持向量机四种方法构建了财务危机预警模型,并用2009年至2012年间24家同行业上市公司作为检验样本对模型进行了检验。研究结果表明:第一,人工智能方法所构建模型的预测准确率比传统方法构建模型的准确率高;第二,资产净利率和营业收入增长率是区分机械、设备、仪表行业上市公司财务状况优劣的重要指标。
In this paper, the data of 74 A-share listed companies in machinery, equipment and instrumentation industry from 2001 to 2008 are taken as research objects. The financial crisis early warning model is constructed by using four methods of multiple discrimination, logistic regression, BP neural network and support vector machine respectively. From 2009 to 2012, 24 listed companies in the same industry were tested as the test samples. The results show that: first, the accuracy of the model constructed by artificial intelligence method is higher than the accuracy of the traditional method; second, the growth rate of net assets and operating income is the difference between the financial status of listed companies in machinery, equipment and instrumentation industries Pros and cons of important indicators.