Based on the PCA of Genetic Neural Network Prediction of Stock Indez

摘要：

Data forecast occupies an important position in the financial investment field, the selected input variables affect the speed and accuracy of forecasts, traditional methods of selecting input variables subjective, and forecast ineffective. Combine Genetic Algorithms with BP neural network, using GAs global search optimize BP network structure parameters, overcome the local convergence and other issues of BP algorithm effectively. Used principal component analysis(PCA) selecting input variables, and GA-BP hybrid modeling applied to the Shanghai stock index prediction. Experimental results show that this method improved the prediction accuracy and achieved a better prediction.

作者: Jing Zhi Dongmei Zhang Pengfei Jiang

作者单位: Department of Computer Science, China University of Geosciences(Wuhan) 430074 China University of Geosciences Arith Geosciences Computer institute of China University of Geosciences

会议类型: 国际会议

会议名称: Third International Symposium on Intelligence Computation and Applications(ISICA 2008)(第三届智能自动化、计算与制造国际研讨会)

会议地点: 武汉

会议语种:英文

页码: 96-99

在线出版日期: 2008-12-19（万方平台首次上网日期，不代表论文的发表时间）