Research Of Financial Early-warning Model On Evolutionary Support Vector Machine Based On Genetic Algorithms

Financial crisis is one of the serous problems that Chinese enterprises face. In China stock markets, listed companies have a loss and can't be profitable, there was danger of delisting. 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 to establish financial crisis alarming system of financial affairs to guard against the emergence of financial crisis.Support vector machine is a new learning machine, and it is based on the statistics learning theory and attracts the attention of all researchers. Recently, the support vector machine (SVM) has been applied to the problem of financial early-warning prediction. The SVM-based method has been compared with other statistical methods and has shown good results. But the parameters of the kernel function which influence the result and performance of support vector machine have not been decided. Based on genetic algorithms, this paper proposes a new scientific method to automatically select the parameters of SVM for financial early-warning model.According to the analysis of the demonstration, the forecast precision of warning model of financial crisis based on genetic algorithms and evolutionary support vector machine is high, and any special hypothesis are not needed in this method. In addition, explanation of some localization of the alarming model itself is described, and my suggestion for future research.