English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Stock price index (SPI) prediction is essential to investors when they make investment decisions. However, due to the intrinsic complexity and non-stationary of SPI, accurate SPI prediction has been a challenge task for a longtime. Compared to a quantity of single algorithms, hybrid methods always have higher prediction accuracy. Based on the theories of genetic algorithm (GA), grey model (GM), back-propagation neural network (BPNN) and support vector regression (SVR), in this paper, two hybrid models named GA-SVR-GM and GABPNN-GM are proposed for improving the prediction accuracy of Composite Index in Shanghai Stock Exchange (SHSE) and Component Index in Shenzhen Stock Exchange (SZSE). The SVR (or BPNN) is first used to forecast SPI and then with the obtained errors GM is constructed taking into account the different patterns that the SVR (or BPNN) cannot identify, reducing with the final errors. Moreover, in order to obtain the better forecasting results of SVR (or BPNN), the model parameters are optimized by GA. Two prediction cases of SPI are used to test the performance of the proposed hybrid models. Compared with the random walk (RW), SVR, and BPNN, the simulation results show that the GA-SVR-GM and GA-BPNN-GM consistently have the minimum statistical error of the root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). Thus, it can be concluded that such improving methods are effective.

An Experimental Investigation of Two Hybrid Frameworks for Stock Index Prediction Using Neural Network and Support Vector Regression