The risk of block chain financial market based on particle swarm optimization

In order to effectively measure the risk of China’s block-chain financial market, in this study, combined with KMV model, which is widely used in the world, the risk prediction model suitable for China’s financial market has been found under the revision of particle swarm optimization algorithm. Based on the analysis of the data of more than 2,900 A-share companies in Beijing, Shanghai, and Guangzhou, the optimal short-term liabilities and the optimal long-term liabilities coefficients of 3.68 and 1.72 for China’s financial market have been found. Through empirical analysis and verification, the ROC curve shows that the short-term debt and long-term debt coefficients 1 and 0.5 of the traditional KMV model cannot distinguish ST shares from non-ST shares in China’s financial market, while 3.68 and 1.72 can distinguish very well. It is proved that the modified KMV model based on particle swarm optimization algorithm can identify the credit risk of Listed Companies in China’s block chain financial market very well.