Research On Quantitative Timing Of 50ETF Options Based On Local Fuzzy Information Granulation And Support Vector Machine

Options is a kind of trading of power,it is an important part of the modern financial market,which originated in the European and American markets in the late eighteenth century.With the development of China's Financial Market,the function of option is increasing,and the research on option investment is more and more.In recent years,quantitative investment with its own advantages such as timeliness,discipline,systematic and so on,has been paid more and more attention by some investment institutions.In this paper,the 50 ETF options quantitative timing model based on SVM and local fuzzy information granulation theory is constructed,which is used to mine and analyze the implied information in 50 ETF options of Shanghai Stock Exchange,and track and predict the rise and fall of 50 ETF options to solve the shortcomings of the current quantitative investment strategy in forecasting accuracy and cumulative income.At last,the feasibility and effectiveness of this algorithm are proved by the experimental results and theoretical analysis.The main work of this paper is as follows:1.In order to overcome the problems such as the timeliness of options and the wide range of price fluctuation,this paper proposes to predict the rise and fall of50 ETF options by tracking the 50 ETF price of Shanghai Stock Exchange according to the price relationship of 50 ETF and 50 ETF options.The feasibility of the proposed algorithm is tested by empirical analysis.2.The traditional technical analysis and fundamental analysis are weak to the option market,and the performance of the current quantitative investment model is insufficient.In this paper,a nonlinear data mining algorithm based on local fuzzy information granulation and SVM is proposed to analyze options market.3.In order to remove the noise and retain the details of the market data,this paper proposes an optimal processing strategy by using multi-day market as sample feature and local fuzzy information granulation in two aspects of sample feature selection and sample marking.The feasibility and effectiveness of this paper are tested from various aspects such as global market and local market.In order to improve the accuracy of prediction,the genetic algorithm is used to find the optimal parameters of SVM in the model constructionThe empirical results show that compared with other methods,the proposed option quantitative timing algorithm have achieved good forecasting accuracy and income in both global market and local market simulation transactions of the historical data.The algorithm presented in this paper is reliable and effective,and has certain reference value and guiding significance in 50 ETF option investment.