Listed Companies In The Classification Of Financial Forecasting Model And Its Application Research

With the implementation of the new bankruptcy law and the development of China's stock market, listed companies are forced to face the fact of bankruptcy. Predicting corporate failure is an important management science problem. This is a typical classification question where the objective is to determine which indicators are involved in the failure or success of a corporation, as well as to determine which methodology can show great predicting ability. Despite the complexity of the financial state of real world, a two-class problem has usually been considered to tackle this classification task. Providing a systematic study on the various methodologies that have tried to handle the problem of bankruptcy prediction, we focus on the financial diversification of China's listed companies. Our objective is to introduce a new method to tackle a multiclass corporate failure prediction problem using a set of listed firms in the same industry. We achieve this end by three steps. Firstly, on the basis of Lv Chang Jiang's(2003,2004) thesis, we classify China's manufacturing listed companies into three groups according to their actual financial situation. Then we get a set of firms as our sample according to the real distribution of the whole manufacturing industry. Secondly, Kruskal-Wallis Test, Median Test and Factor analysis as well as cluster analysis to are introduced to determine which indicators can indicate distinguish differences among the three groups. Then three indicators system are built to construct different predicting models. Lastly, applying of SVM model, the one year prior and two year prior as well as three year prior financial predicting models are built.