Research On Green Credit Risk Of Commercial Banks Under The BP Neural Network

In today’s rapid economic development, human beings enjoy their achievements at the same time, conflicts and consider themselves the environment has become increasingly prominent. Global warming, ecological deterioration and other problems gradually caused widespread public concern; the road of economic development of low-carbon emission reduction has become an inevitable trend. In order to address climate change, international conventions, "the United Nations Framework Convention on Climate Change", "Kyoto Protocol" has promulgated. China, as the world’s second largest economy, carbon emissions have been highest in the world. Faced with severe ecological environment, China’s path of sustainable development is an important prerequisite for the way long-term stable economic growth.Green credit is an important initiative to increase the ecological protection, green credit refers to banks and other financial institutions provide loans to business and institutions which do research on ecological protection and construction in accordance with national environmental and economic policy and industrial policy. In recent years, green credit is becoming development, Industrial Bank, Industrial and Commercial Bank of China, Ping An Bank and other banks launch carbon financial products and actively join the Equator Principles. Different between the commercial banks and the ordinary business is risk control, bank business loans facing credit risk, for example, operational risk, interest rate risk and other multiple risks. Credit risk is the most important risk. Many domestic and foreign scholars assess the credit risk of a lot of research, quantitative credit risk models are endless, but the green credit’s research is not perfect, few scholars’ domestic research on green credit risk assessment.In view of this, this thesis constructs the BP neural network model of green credit risk assessment on the basis of literature. Firstly, construct the index system of green credit risk assessment, make the financial indicators, non-financial indicators and environmental indicators as level indicators, establish the 30 secondary indicators; Secondly, use "3?" rule for the quantitative determination of credit risk criteria to calculate the loans business credit risk rating; Again, select 56 listed companies as samples for empirical research, conducted normality test and significant test of its financial indicators, use network analysis(ANP) to environmental indicators and non-financial indicators weight determination, after scoring draw samples according to the expert score, the three types of indicators for factor analysis, get the representative of the common factors; Finally, using MATLAB software to build the BP neural network simulation analysis, the predicted results for selection and use of credit risk assessment methodology to provide a reference.Meanwhile, the green credit risk assessment system can improve the efficiency of the loan prior, the analysis of corporate risk evaluation and classification, and can clearly define the risk profile of the target company. Through the use of a set of analytic tools to detect a variety of potential credit risk, banks optimize loan management technology. What are the risks of a more substantial increase in business to be immediately re-crediting assessment, timely adjustment of the line of credit once discovered?...