Research On Financial Index Investment Strategy Based On Improved Support Vector Machine

With the prosperity of the securities market today,it has become important to obtain effective information from the massive historical data and thus applied to the investment.Investors who follow the risk diversification principle need to focus on the dynamics of the market,but investors who are keen on sector investment need only focus on specific industries.Support vector machine(SVM)is based on statistical learning theory,which can solve many practical problems very well,especially in small sample learning and nonlinear model recognition.In this paper,we focus on the selection and optimization of SVM kernel function,choose SFC Financial Index as the sample,and use SVM to carry on the regression forecast,finally choose the fuzzy information granulation technology to improve SVM.The paper uses the investment strategy to carry on the empirical test finally.Experiments show that SVM based on fuzzy information granularity have better accuracy and extensibility in exponential forecasting and investment strategy.The innovation of this paper mainly includes the following two parts:(1)Choose the SFC Financial Index as the sample,trying to provide advice to investors who focus on the financial sector.(2)Design the investment strategy based on the information-based SVM,trying to provide effective guidance for investors.