Research On Financial Risk Prediction Of Listed Companies Based On PSO-BP Neural Network

In the era of "Internet +",the world economy is becoming more and more globalized and informational.The enterprise’s production and management environment is changing rapidly.The business development of Chinese enterprises is faced with unprecedented opportunities,but it is also subject to environmental factors,such as economic market factors,regulatory factors,social and cultural factors,environmental factors and policy changes.All these unpredictable environmental factors gave the company’s financial situation uncertain,and increase enterprises’ financial risks.At present,many enterprises are still not recovered from the pain of the economic crisis.Because of the external environment deterioration,internal management chaos,serious loss of assets and capital chain problems,the financial situation is worrying.The overall development of enterprises and their own financial risk situation processing is closely linked.Most of the enterprises suffered serious financial crisis or even bankruptcy in the later,because they did not pay enough attention to the early financial problems and took effective measures to deal with the crisis situation timely.It’s unfavorably for the follow-up development of the enterprises.Therefore,more and more attention has been paid to the study of financial risk.In this paper,the financial risk index system of Chinese listed companies is obtained by analyzing the theory of financial risk of listed companies and combining the principle of principal component analysis,particle swarm optimization(PSO)and artificial neural network.In order to improve the accuracy of financial risk prediction,the principal component analysis and particle swarm optimization are used to optimize the BP neural network model,and the input data of the prediction model is improved.The initial weights and thresholds of BP neural network are optimized by PSO algorithm.Based on this,a PSO BP neural network(PSO-BP)financial risk prediction model is built.The empirical results show that the PSO-BP model is more accurate than the traditional financial risk forecasting model based on the financial indicators data of China’s listed companies.