| While the dog-eat-dog market economy is pregnant with the opportunity for development, there are countless risk and crisis hided in it. As to listed company, the situation that it is titled with "ST" plate and even forced to quit listing because of financial crisis grows more and more seriously. It is not only the threat to existence and development of the company failing into the financial crisis, but also brings enormous loss to investors, creditors. So to establish a effective practical pre-warning model on financial crisis, in order to meet interests' increasingly urgent need, has already not merely been an academic problem, but also become an important factor influencing sound development of capital market of our country, and has very important realistic meanings.In this paper, begin with agent technology- rough set theory and ANN technology have been applied to research on financial risk. Based on this method, in this paper, the rough set will be introduced firstly, and at the same time, some algorithm used to knowledge reduction will be discussed;and then, the principal of ANN and tis improved algorithm will be introduced detail. After introduce of the basic theory, we posed a method which combine the rough set and ANN and applied it on the financial risk research of Chinese listed companies.There are five parts in this paper. Firstly, background of research of financial risk and research significance will be introduced, and the statue of research over the world will be further introduced, in addition to explicate the innovation point of this paper. Secondly, basic theory of rough set will be detailed. Using theories of rough set in pretreatment on ANN will avoid the subjectivity in choosing the construction of ANN and strength the efficient. Thirdly, the construction and improved algorithm of ANN will be argued in order to enhance explaining mechanism. Forthly, the basic idea of rough set - Ann model will be detailed. The last, it is conclusion. |
PDF Full Text Request