bp神经元网络及logistic回归比较分析下的上市公司财务风险预警分析word格式论文.docxVIP

优秀毕业论文 精品参考文献资料 Abstract With economic development, the environment of the enterprises are facing more and more volatile in the diversification of investment and operation, increased competition and technological development brought about structural friction, making the modern enterprise than ever facing more difficult to control the risk. Warning is particularly important before the crisis hit. Enterprise risk is not limited to the financial aspects of the business failure often comes from the weak financial risk control. Looking In recent years, several monster bankruptcies, given its fatal blow is often the financial risks of runaway. Each enterprise in the course of business, should always consider the financial early warning management to stifle before the crisis in the controllable range. This paper studies the Chinese manufacturing listed companies, theoretically more suitable for the prediction of the BP neural network technology to establish financial early warning model to predict the crisis may be coming in the future, whether it is more accurate and effective. This paper first describes the theoretical basis of the financial early warning research defined financial risk related concepts. Clarify the basic theory, combined with the results of previous studies, the establishment of a financial early warning indicator system model. Follow by listed companies in Chinas manufacturing industry as a study sample financial early warning model and research. Select 69 non- ST and 69 ST companies as the study sample. Select a representative indicator of financial and non-financial indicators. Screened by principal component analysis method, the representative of the financial indicators, the index system was established in the inclusion of non-financial indicators. Principal component analysis is used to extract representative indicators. Finally, factor analysis index system, the establishment of the BP neural network model is used to calculate the prediction acc