SME Debt Collection Credit Risk Measurement

Assemble bond for small and medium enterprises (SMEs) is a financial innovative product emerged during recent years in Chinese capital market, which is major break through of SMEs financing. It is not only valuable for Chinese SMEs to promote the growth of SMEs assemble bond by researching, but also contributes to the study of SMEs financing. Like any other new born financial product, there are some problems waiting to be solved. One key problem is the measuring of credit risk. Because the issuers of Assemble bond are all SMEs, they Possess high credit risks. Moreover, after bonded together, the measuring and controlling of general credit risk become very complex. This paper divide the credit risk into two parts:individual credit risk and the overall credit risk.The small and median enterprises assemble bond financing of individual credit risk facing many realistic problems, such as small sample, nonlinear, high dimension and so on, the traditional evaluation method is difficult to apply. In order to make up for the shortcomings of the traditional evaluation methods, and enhance the credit risk measurement accuracy, this paper established a more applicable credit risk evaluation index system, and introduce support vector machine model that based on statistical learning theory. Select the radial basis kernel function as the kernel function of support vector machine, through the data conversion and scaling, parameter optimization, finally obtained good classification effect of small and median enterprises assemble bond financing of individual credit risk measurement model. Through the test of actual data, the forecasting accuracy reached90.77%, the model has strong applicability.The overall credit risk of SME collective bonds includes both the cyclical nature of default risk Caused by the systemic risk, but also including the relationship led to the infectious risk of default. In this paper, improve factor model to build models Ⅰ, to study the cyclical nature of default risk of a collection of bonds; Next, introduce default contagion to build model Ⅱ, to research the overall credit risk of collection of bonds, and to analyze the effect of default contagious phenomenon to probability of corporate default and default correlation. Based on the second model, When the system risk factors to determine the value of the path, the collection of bonds for breach of contract the infection process is shown as a continuous time Markov chain, using conditional transition probability matrix corresponding to the "Kolmogorov" differential equations can be derived the probability of a collection of bonds of each non-compliance and the joint probability distribution of corporate defaults time. Finally, by numerical example, concluded that:the relationship between enterprises to increase their joint default probabilities and default a correlation, the nature of breach of infection is a default correlation.