Research On Dynamic Financial Pre-Warning Models Based On Theory Of Grey Prediction And Artificial Neural Networks

With the development of the global economy, continuity assumption in tradition financial affairs theory is tottered, uncertainty that enterprises facing with has gradually been enhanced, so more and more attention have been paid on the financial condition of the enterprises by different market entities, and the great demand on the financial pre-warning seems to be more and more urgent. Comparing with abroad researches on the financial pre-warning, there is a gap on our pre-warning theories to a certain extent, for the developing stage of market economy and immature of capital market in China. Generally there are some financial indexes appearing anomalous as the financial condition of enterprises deteriorates. Such anomaly seems to be an abrupt change at one point, while it is a variation generated from a gradual advance process in fact. So taking account for our national condition, this thesis has tried to take the capital market of our country as the foothold, make a discussion on the establishment of the dynamic financial pre-warning models.The research purpose of this thesis is that, to set up an indexes system for pre-warning the financial crisis of enterprises with the statistical methods, and establish the dynamic financial pre-warning model, make a pragmatic prediction to fulfill the pre-warning on the underlying financial crisis of enterprises, by the theory of grey prediction and the artificial neural network method.The very core of this research is that, to establish an effective dynamic financial pre-warning model for high accuracy prediction by the combination of the theory of grey prediction and the artificial neural network method. On writing arrangement, the thesis divides six parts mainly. The first part is the introduction, which generally introduces the research purpose and significance of this thesis, the summary of the financial pre-warning researches both home and abroad, and the research main contexts and research methods; The second part is the comparison on the financial pre-warning methods existent, which compares the different methods by categories, makes a further analysis on the limits of existent methods, and proposes the improve thoughts of this research based on that; The third part is the basic theory, which makes a summary of the referent theories exerted on the research, and exposit the comparing mechanism of the grey prediction theory and the artificial neural network method concise; The fourth part is the frame work of the model, which illuminates the research designs step by step, such as the definition of the financial crisis, the method of sample select, the select and definition of the pre-warning variables, and makes an exposition of the establishment procedures of the whole models at last; The fifth part is the financial pre-warning based on the theory of grey prediction and artificial neural network, which mainly demonstrate the model establishment in the concrete, dividing into four part to carry out the part of pragmatic research integrally, building of indexes system, establishment of BP neural networks, dynamic financial pre-warning and test, analysis on the pre-warning result; The sixth part is conclusion, which sums up the main results of the whole research, clarifies the innovative points, and makes a discussion on the limits and future study directions of the research in this thesis.Through the pragmatic research, the thesis has obtained following conclusions. Firstly, enterprises caught in the financial crisis is a synthetic event, which can be reflected integrally by four indexes, current ratio, earnings per share, net assets per share, and cashes per share; secondly, it is can not be ignored the trend effect of the time series of financial indexes, as evaluating the financial condition of enterprises, which predicts significant on the financial pre-warning; thirdly, effectively the dynamic financial pre-warning model predict the underlying financial crisis at the incipient stage, based on the combination of the theory of grey prediction and the artificial neural network method.