Research Of Financial Crisis Alarming Based On Rough Set And Neural Network

Financial crisis is one of the serous problems that Chinese enterprises face. It not only menaces enterprises'subsistence and development, but also influences the benefits of the investor, the creditor, and the whole society. 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 financial crisis alarming system of financial affairs to guard against the emergence of financial crisis.This paper introduces relevant literature in and abroad, analyses and compares existing methods of crisis alarming. There are many methods to handle this financial crisis problem, but the most widely used technique is statistical methods including Multivariate Discriminant Analysis(MDA) and Logistic Regression, etc. The studies using MDA have encountered, however, some methodological problems. The violation of the underlying normality assumption of independent variables causes the biased results. The Logistic method, as primary alternative statistical method, also requires different kinds of statistical assumptions which limit the usefulness of its application. So this paper chose one of alter native methods, neural network, for the financial crisis alarming problem.Rough set theory is a relatively new soft computing tool to deal with vagueness and uncertainty. It has received much attention of the researchers around the world. Rough set theory has been applied to many areas successfully including pattern recognition, machine learning, decision support, process control and predictive modeling. By analyzing two methods, neural network and rough set, we connect the theory of neural network with rough set and establish the model of financial crisis alarming based on rough set and neural network.According to the analysis of the demonstration, the forecast precision of alarming model of financial crisis based on rough set and neural network is very high, furthermore, any special hypothesis are not needed in this method. In addition, explanation of some localization of the alarming model itself is...