| 支持向量机回归集成股市预测模型 |
| |
| 引用本文： | 汪灵枝,赵秋梅,韦增欣.支持向量机回归集成股市预测模型[J].广西工学院学报,2010,21(3):28-32. |
| |
| 作者姓名： | 汪灵枝 赵秋梅 韦增欣 |
| |
| 作者单位： | 1. 柳州师范高等专科学校,数学与计算科学系,广西,柳州,545004;广西大学,数学与信息科学学院,广西,南宁,530004
2. 广西大学,数学与信息科学学院,广西,南宁,530004 |
| |
| 摘 要： | 利用基于主成分分析的支持向量机回归集成技术,提高集成个体差异度,生成一组优良的神经网络集成个体,将股票指数函数拟合成高维核空间的线性回归函数,求出一个满意的全局最优解,提高股指预测精确度,继而建立一个新型股市预测模型.试验表明,该模型能有效提高神经网络集成系统的泛化能力,预测精度高,稳定性好.
|
| 关 键 词： | 神经网络集成 支持向量机 主成分分析 |
A Model for Stock Market Forecasting on Ensemble of Support Vector Regression |
| |
| WANG Ling-zhi,ZHAO Qiu-mei,WEI Zeng-xin.A Model for Stock Market Forecasting on Ensemble of Support Vector Regression[J].Journal of Guangxi University of Technology,2010,21(3):28-32. |
| |
| Authors: | WANG Ling-zhi ZHAO Qiu-mei WEI Zeng-xin |
| |
| Affiliation: | 1.Department of Mathematics and Computer Science,Liuzhou Teachers College,Liuzhou 545004,Guangxi,China;2.College of Mathematics and Information Science,Guangxi University,Nanning 530004,Guangxi,China) |
| |
| Abstract: | In this paper,ensemble of support vector regression is implemented which is based on Principal Component Analysis Method.Then it can improve the diversity factors of the neural network ensemble individuals and generate a set of excellent ensemble individuals.Using this technology the stock index function is fitted into the linear regression function in high dimension kernel space.Meanwhile a satisfactory global optimal solution can be gotten to improve prediction accuracy.Thus a novel model for stock market forecasting is made.Tests show that the model has advantages of high accuracy,good stability and can effectively improve the generalization ability of the neural network ensemble system. |
| |
| Keywords: | neural network ensemble support vector machine Principal Component Analysis |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
