Research On Credit Rating Of P2P Network Lending Platform

Since 2005, the birth of Zopa-the world’s first P2 P network lending platform in the UK, as an emerging market borrowing mode, with the development of Internet technology,since the development of the world’s A new force suddenly rises. 2007, the first domestic P2 P network lending platform pat on the line, and in 2013 ushered in the development of large-scale, the momentum is very rapid. For the financial market of our country has injected new vitality, which provides a new way for the consumer’s personal credit and small micro enterprise financing. P2 P network lending platform to effectively supplement the traditional banking services to small and micro enterprises, effectively meet the financing needs of small and medium enterprises and individuals, has become an effective complement to traditional finance, and thus the explosive growth. Behind the development of China’s P2 P network lending blowout, reflecting the traditional lending model is difficult to meet the practical needs of private lending.P2P network lending industry has solved the problem of financing, but also to a certain extent, the efficiency of capital allocation can be improved, but the risk can not be ignored. According to incomplete statistics, as of September 2015, the number of closed foot platform has reached 1004. However, P2 P net loan is a new thing in China. On the one hand, there are some drawbacks, such as identity ambiguity, lack of legal system and supervision. On the other hand, the credit system which is closely related to the credit system has not been realized. This makes the development of P2 P network in China is facing many new problems, which hinders the further development of P2 P net loan industry in China.At present, there is a serious asymmetry of information between investors and the P2 P network lending platform, making it difficult for investors to choose the high quality P2 P network lending platform, the P2 P network lending platform is difficult to build trust, P2 P network lending platform to increase the cost of the platform, causing the credit crisis. In order to solve the problem of asymmetric information, credit rating. Through credit rating,P2 P network lending platform can be integrated into the comprehensive assessment, form a professional credit analysis, at the same time, investors can understand the real situation of the P2 P network lending platform, to provide investors with risk information, so as to increase the confidence of investors on the P2 P network lending platform, select the right investment platform, so that the loss of funds to achieve the value, which will promote the development of the entire industry.In this paper, through the summary of the relevant literature, this paper expounds the credit rating theory, the information asymmetry theory, the comprehensive risk management theory and the credit factor analysis method, and then analyzes the credit rating of P2 P network lending platform in China. After that, we study the rating index system of the mainstream institutions in China, combined with the natural characteristics of the P2 P network lending platform, and build a P2 P network credit rating index system which is suitable for our country. Then, the improved BP neural network model based on the traditional BP model is described. In this paper, we use 12 P2 P network lending platform sample of 33, two 8 level indicators, as well as the actual rating results, using the improved BP neural network model, through the Matlab software simulation training, so that the overall error between the network model output and the actual rating results meet the requirements, so as to train the P2 P network lending platform credit rating model. And try to predict the rating of the platform for risk prevention in advance to prevent the occurrence of risk. At the end of this paper, we demonstrate the accuracy and applicability of the model. The results show that the results of the training network model are in line with the actual situation of the platform, and more correctly reflect the company’s credit rating. Therefore, this model can predict the credit level of the P2 P network lending platform.