基于遗传算法的动态递归网络的股价预测  

Stock index forecast based on dynamic recurrent neural network trained with GA

作　　者：房毅宪[1] 王宝文[2] 王永茂[1] 

机构地区：[1]燕山大学理学院,河北秦皇岛006004 [2]燕山大学信息科学与工程学院,河北秦皇岛006004

出　　处：《燕山大学学报》2007年第4期359-363,共5页Journal of Yanshan University

摘　　要：为了对股票市场进行更准确地监测预报,根据股市的动态特性,提出了应用动态递归神经网络进行实时建模预测,并采用遗传算法进行在线学习,提高了网络性能,较好的描述了股市的动态特性。通过对某上证股价的预测,验证了该法的有效性。In order to forecast the stock market more accurately, according to the dynamic property for the stock market, the real time modeling forecast is proposed via dynamic recurrent neural network and GA is used to study online, then the network performance is improved and the dynamic characteristic of stock market is better described. By forecasting Shanghai negotiable securities index, it shows better validity.

关 键 词：动态性 神经网络 股价 遗传算法 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] F830.9[自动化与计算机技术—控制科学与工程]