Correlation And Risk Prediction Of Financial Markets Based On Copula

In the process of China's rapid economic development,China's economy is striving for stability and worrying about stability.The downward pressure on the economy has increased,especially in the context of China-US economic and trade frictions.The Chinese economy is facing a severe external environment.The combination of inadequate and unbalanced problems facing our own development makes it more difficult to stabilize growth and prevent risks.From the demand side,consumption growth continues to be weak.Although real estate development investment has remained high,infrastructure investment has rebounded slightly,but due to the decline in industrial enterprise profit growth and the decline in import and export growth,manufacturing investment has fallen sharply,and total investment has increased.Quickly dropped.In this economic environment,financial markets play an increasingly important role.The volatility of financial assets and the relationship between volume and price are important determinants in risk management and investment in financial assets.Optimizing the portfolio of financial assets also It has always been the research focus of scholars at home and abroad.Therefore,this paper uses financial high-frequency data to study the stock market's price volatility,volume-price relationship,and optimal investment portfolio.The main work is as follows:First,the GK volatility is introduced,and the Markov mechanism is used to transform the Copula model to study the tail of financial data volatility.The economic period is divided into three periods:the period of economic recovery,the period of economic development,and the period of economic downturn.At the same time,the mixed Copula model is used to study the volume-price relationship in different economic periods.The study found that:(1)the mechanism conversion SJC Copula model has a better fitting effect on the tail dynamic characteristics of the volatility aggregation of financial data than other Copula models.And the tail of the volatility cluster has obvious asymmetry,and the correlation coefficient of the upper tail is obviously larger than that of the lower tail.(2)The transition probability and duration are the largest during economic development,followed by the economic downturn,and the smallest during economic recovery.(3)At the tail of the volume-price relationship during the period of economic recovery and economic development,the correlation at the upper end is significantly greater than the correlation at the bottom,indicating that when the stock market rises,it is often accompanied by high volatility and high transaction volume.During the economic downturn,the opposite is true.Then,using the R-Vine Copula asset portfolio selection mechanism,the Shanghai Composite Index selects the optimal investment portfolio in different economic periods,and measures the corresponding portfolio risk.The study found that:(1)The correlation structure between the top ten industry indexes was better than that of C-Vine and D-Vine by R-Vine.(2)With the increase of the tree level in the R-Vine structure,the lower-end net correlation coefficient between industry indexes gradually decreases.In the period of economic recovery,when considering 6 or more industries at the same time,the possibility of all industry indexes falling at the same time is low.In the period of economic development,when considering 5 or more industries at the same time.All industry indexes are less likely to fall at the same time.In a period of high volatility,when considering 7 or more industries at the same time,the possibility of all industry indexes falling at the same time is low.(3)As the number of investment industries in the investment portfolio increases,the risk of the investment portfolio gradually decreases.In addition,the investment portfolio selected through the R-Vine structure is more selective and lower risk than the investment portfolio selected by traditional methods.