Financial Crisis Warning For Listed Companies In China's Steel Industry

As an important pillar industry of China's national economy,the substantial and stable development of the steel industry plays a crucial role in the process of industrialization and urbanization in our country.While in recent years,the global economy continues to slow,iron ore and energy are so high prices,with the pressure of economic downturn and the decline of market demand,the accumulated contradictions and problems are exposed gradually with the rapid development of steel industry.The problem of overcapacity is particularly prominent,resulting in a sharp decline in profits margin and an increase in financial risk.The steel industry in the event of financial risk,not only endangers its own survival and development,but also brings losses to other related industries.Therefore,how to accurately predict and effectively control the enterprise risk and financial crisis,to ensure the healthy and long-term development of the enterprise is an important issue faced by the steel industry.First of all,this paper makes a literature review on the domestic and foreign scholars' researches on the connotation of financial crisis and the early warning of financial crisis,and then the related basic theories of logistic regression model and BP neural network model are discussed.Based on the definition of the connotation of financial crisis,combined with the current development status of listed companies in steel industry,from the 55 indexes disclosed,we set up an early warning index system which including 22 financial indicators and 9 non-financial indicators.Then we apply the logistic regression model which is widely used in the research field of financial crisis early warning and the BP neural network model which is newly developing in recent years,based on two sets of early warning index systems(financial index system which commonly used in the current research,and the early-warning index system including non-financial indicators),the empirical analysis is carried out respectively,and the models are compared and evaluated.The results show that the accuracy rate of the logistic regression model which based on two sets of index system reaches 16.7%and 33.3%respectively in the prediction of financial crisis,while the prediction accuracy of BP neural network reaches 50%and 83.3%respectively,it can be seen that the accuracy of the financial crisis early-warning model based on the BP neural network is obviously better than the logistic regression,at the same time,the index system including non-financial indicators is also much better than the financial index system on the effect of financial crisis early warning.The output of the model is the probability value,the early warning manifests that when the probability value exceeds the threshold value,we can determine that the financial status of the enterprise is not optimistic and needs to take measures to control the risk.At the same time,the study can be used as a reference method for the steel industry and the enterprise themselves.