A Study Of Financial Distress Prediction Of Listed Corporations With Sport Vector Machines Model

Research on financial distress prediction is one of the most important research subjects. It has not only high academic value but also enormous practical value. In Chinese developing but not mature security market, whether the listed companies are healthy or not, will affect related interests of investors and creditors. The research of their financial situation is of grate importance. If we can generalize the research results into the other no-listed companies, it will be more significant to guide the management and risk prevention of the enterprises.This article firstly reviews previous empirical results of the research on the financial predicting models. Secondly, based on the summary of previous research methods and results, one hundred and twenty two A Publicly listed firms, which are special treated (ST) in the year of 2003 and 2004, are selected as samples. And according to the matching criterion of the same industry and size, the equal quantity firms whose financial situation is good are selected as control samples. Furthermore, this paper uses factor analysis to abstract the most important nine factors from nintheen financial indexes, then seven common factors have been selected to set up the new financial index system. At last, we use support vector machines to set up a new financial distress prediction model., which gives the direction of the enterprise operation.In order to test the validity of financial distress prediction model ,we use the same samples and financial data to establish a logistic regression model,through comparing the accuracy of these two forecast models,we find that because of its unique properties, support vector machine model has the superiority of any other method, and it is a method of innovation.