您的位置:首页 > 论文页面
基于灰色粒子群神经网络的期货价格预测
发表时间:2008-06-30 浏览量:2359 下载量:963
全部作者: | 王海军,白玫,贾兆立,覃丽萍,李聂 |
作者单位: | 首都师范大学信息工程学院;中国社会科学院工经所 |
摘 要: | 针对目前采用BP神经网络对中国期货市场进行价格预测时存在的问题,本文从网络输入和网络参数两个方面对BP网络模型进行优化。首先用灰色关联度分析法进行输入变量的筛选,找出影响输出变量的重要因素作为网络输入,然后采用改进的粒子群算法对网络参数进行优化,将经过选择优化后建立的BP神经网络模型用于期货价格预测。仿真结果表明,经过优化后的BP神经网络模型在运行速度和预测精度方面明显优于单纯的BP神经网络模型。 |
关 键 词: | 人工智能;计算神经网络;期货;灰色关联分析;粒子群算法;BP神经网络 |
Title: | The futures price forecast based on grey PSO neural network |
Author: | WANG Haijun, BAI Mei, JIA Zhaoli, Qin Liping, LI Nie |
Organization: | Department of Information Engineering, Capital Normal University;Institute of Industrial Economics, Chinese Academy of Social Sciences |
Abstract: | There are some problems existed in the price forecast by BP neural network of Chinese futures’ market. This paper optimized the model of BP neural network from the input and parameters of network. First, in order to identify important factor in the network’s input, it used grey correlation analysis to filtrate input variables. Then the particle swarm optimization algorithm was used to optimize the parameters of BP neural network, and after the network was optimized, the model was used to forecast futures price. The simulation results showed that optimized BP neural network model was superior to simple BP neural network model in the running speed and accuracy of forecasts. |
Key words: | artificial intelligence; neural network computing; futures; grey correlation analysis; particle swarm optimization algorithms; BP neural networks |
发表期数: | 2008年10月第12期 |
引用格式: | 王海军,白玫,贾兆立,等. 基于灰色粒子群神经网络的期货价格预测[J]. 中国科技论文在线精品论文,2008,1(12):1348-1353. |

请您登录
暂无评论