Research On Financial Risk Of Passenger Vehicle Enterprises Based On BP Neural Network Optimized By Fish Swarm Algorithm

With the continuous development of China’s science and technology and economy,the automobile industry has gradually developed into a pillar industry of the national economy.However,under the situation of fierce competition in the domestic and international markets,due to a series of problems such as limited research and development funds,the outflow of technical personnel,and the weak influence of independent brands in the automotive industry in China,the future development of the automotive industry is facing serious obstacles.As a global automobile production and sales country,China has great market potential.Therefore,for enterprises in the automotive industry,effective risk management is essential.As the core of risk control,financial risk is the top priority for managers in assessing and controlling risks,controlling financial risks within a reasonable range,and strengthening the development capacity of the automotive industry to maintain the healthy and sustainable development of China’s economy.If the enterprise fails to understand its financial risk status in time and make different countermeasures according to its financial status,the enterprise will gradually fall into financial distress,resulting in adverse consequences such as financial crisis and corporate bankruptcy.In the entire automotive industry,passenger cars dominate the market.This paper selects listed passenger car companies in China’s automobile industry as the research object,and analyzes the current financial risk status of domestic passenger car companies to obtain the financial risk evaluation index system for domestic passenger car companies.In order to improve the accuracy of the model’s financial risk prediction,the input layer data and related parameters of the traditional BP neural network were optimized by using principal component analysis and artificial fish swarm algorithm to simplify the data of the input layer of the risk prediction model and use artificial fish.The global optimization function of the swarm algorithm optimizes the initial connection weights and thresholds of the traditional BP neural network.Based on this,an artificial fish swarm algorithm is used to optimize the financial risk model of the BP neural network and the validity of the model is verified.The comparison with the traditional BP model’s discriminative effect proves that the BP model optimized by the fish school algorithm has a higher discriminant accuracy.The results show that compared with the traditional BP neural network,the artificial fish school optimized BP neural network model has higher accuracy in discriminating the financial risks of passenger car companies.In addition,this method can be implemented into the financial risk control of other enterprises in order to better grasp the financial status of the enterprise’s operating process,which is conducive to the long-term development of the enterprise.