Abstract
under the background of economic globalization and financial integration, the financial market has gradually become an important part of the current market system. Besides the stock market is an important part of the financial market. From a macro perspective, government regulatory departments and policy makers can monitor the stock market by using stock index prediction model, so as to adjust macroeconomic policies in time. From a micro perspective, individual investors and enterprise investors can use stock index prediction model to improve their ability of avoiding risks, so it is of practical significance to build a high-precision stock index prediction model. In this paper, the EMD (Empirical Mode Decomposition) method and SVR (Support Vector Regression) algorithm were combined to construct the EMD-SVR stock index prediction model, and the IEME (Improved Extreme Mirror Extension) method was proposed to suppress the end effect of EMD method to form the IEME-EMD-SVR model. Finally, through the empirical research on the transaction price data of Shenzhen Stock Exchange Component Index and the comparative study on EMD-SVR model and IEME-EMD-SVR model, it is proved that IEME-EMD-SVR model has higher prediction accuracy and lower time complexity. The proposed model has provided a powerful tool for stock index prediction and provided a new way of thinking for the application of time-frequency analysis in financial time series.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.