An Empirical Study Of China's Listed Companies' Financial Crisis Based On Neural Network Prediction

Financial distress is one of the serious problems that Chinese listed company faces, because it greatly affects the financial decision making of investors, credits, and bank officers. Therefore, the academic circles attach importance to the research on financial distress and its prediction. There are many statistical procedures to handle this financial distress prediction problem. The most widely used classification technique is statistical methods including MDA and Logistic, etc. Since Airman introduced the use of MDA to financial distress prediction, MDA has been widely applied to the business classification, including bankruptcy prediction, credit rating, and bank loan classification, 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.As one of alternative methods, it is well known that neural network approach is very promising for the financial distress prediction problem. A neural net represents a nonlinear discriminant function as a pattern of connections between its processing units. In this paper, we propose a new neural network model to the financial distress prediction problem. Based on the financial data of the distressful companies in Shenzhen and Shanghai stock exchange during the year from (t-2) to (t-4), we use 50 financial ratios and 17 principal components as input and the probability as output. Empirical results show that neural network is a promising method of financial distress prediction in terms of predictive accuracy, adaptability, and robustness.