Study Of Financial Crisis Prognosticating With Non-financial Index And Data Mining Methods

Financial crisis not only menaces enterprises' subsistence and development but also influences the benefits of the investor, the creditor, and the state. With the development of capital market and the reform of market economy system, the complexity and uncertainty in economic field becomes increasingly evident, and it comes to be widespread that financial crisis and bankruptcy occurs in enterprises. Therefore it is one of urgent tasks of financial management to establish forecasting system of financial affairs to guard against the emergence of financial crisis.Made a study of listed companies of China (24 companies in financial crisis and 24 companies in normal), and made use of 4 kinds of studying methods, we set up a forecasting model of listed companies' financial crisis whose time span is 6 years in the dissertation. The thesis mainly discusses the influence of non-financial index to the model, contrasts the effects of the way using non-financial index with the way without using non-financial index, compares and contrasts the prognosticating effects of 4 models which are set up according to the following 4 kinds of ways: the Discriminate analysis, the Logistic analysis, Artificial Neural Network (ANN) , and data mining, finds that using non-Financial index can advance the degree of accuracy of the forecasting of Financial crisis in the Listed companies, and to calculate with C5.0 of data mining will be more accurate than other statistics methods and non-statistics ones.Different from the formal study methods, one new method is used in this dissertation. When setting up forecasting model of financial crisis, both the domestic experts and the foreign ones base their study on the hypothesis of precise accounting information which is often unprecise in most listed companies of China and foreign countries because of the dishonest profit manipulating, which makes the application of forecasting system of financial crisis unpractical. Therefore in this dissertation non-financial index is used in the forecasting system of financial crisis and mature calculating method C5.0 of data mining...