Research on Forecasting Method of Stock Index Yield and Volatility Based on Hybrid Intelligent Algorithm

Chinese mainland's stock index futures have just been launched, and hedging is the main tendency of people's investment. Whether investing or buying or selling stocks, it is necessary to anticipate the future fluctuation direction of the rate of return, so as to adjust their portfolio accordingly, although it is impossible to predict completely and accurately. In this paper, the closing price of CSI 300 index is decomposed by using EEMD (Ensemble Empirical Mode Decomposition) algorithm based on hybrid intelligent algorithm, and 10 intrinsic modulus functions and one residual function are successfully obtained. Finally, the CSI 300 index prediction model based on EEMD-LSTM(Long Short-Term Memory) model is established, and various evaluation indexes are established to measure the performance of the model, and the prediction effect of the reference model is compared. The GARCH-Jump model is established and an attempt is made to study the price fluctuation of Shanghai and Shenzhen 300 stock indexes based on MCMC(Markov Chain Monte Carlo) simulation method. The final results show that EEMD-LSTM model has better prediction performance.