The Causality Analysis Of Stock Market And Unemployment Rate And Forecast Research

The stock price index can effectively reflect the price level of whole stock market,as well as help government officials and investors handle the changes of stock and the overall social economy.As an important macroeconomic variable of a country,the unemployment rate is not only a crucial reference indicator for government decision-making and national economic development,but also a helpful measure of the country's economic stability and living standard.So the unemployment rate is regarded as "Crown jewel" among all economic variables.Therefore,detecting the relationship between the stock market and the unemployment rate,finding the changing rule of stock index are of great significance to the government and investors.We investigate the causal relationship between the unemployment rate and the stock index,then,explore the impact of economic crisis on causality.Finally,we add the unemployment rate as one of the factors that affect the stock volatility to predict stock price.The main work and achievements are shown as follows:(1)Taking the Dow Jones Industrial Average Index and the unemployment rate in the United States as an example,we firstly study the causality between stock index and unemployment rate.By constructing auto-regressive model and joint regression model to detect the Granger causality and New causality,then based on the significance test,it is theoretically proved that the change of unemployment rate affects the fluctuation of stock index.(2)When analyzing the causal relationship between variables,we regard the economic crisis as demarcation basis and divide the whole time period into economic crisis periods and non-economic crisis periods.Experiments show that unemployment rate causes the volatility of stock index during each economic crisis period or non-economic crisis period.Besides,we cannot find the law during whole periods which include economic crisis.In addition,comparison between Granger causality method and the New causality method proves that the New causality is more applicable in some aspects.(3)In order to confirm that the change of unemployment rate is one of the factors that affect the volatility of the stock price index,we carry out stock prediction experiment based on the unemployment rate information.In this experiment,we addthe time series of unemployment rate as one of the factors that affect the stock changes to the independent variables of the stock forecast,and then use the wavelet neural network based on genetic algorithm and the support vector regression prediction algorithm to conduct experiment.Compared with only using stock-related variables to predict the stock market volatility,the results show that the prediction accuracy of the two algorithms is improved after the unemployment rate is added.Therefore,it further illustrates that the unemployment rate is the factor that cause the stock price volatility.