摘要
以股市的可预测性为基础,以可量化股价影响因素作为输入变量,提出了将遗传算法与BP算法相结合用于股市价格预测的人工神经网络模型学习算法;建立了基于人工神经网络的股价预测模型。通过对海信电信(600060)的股票收盘价和大盘指数为预测目标进行了股市预测的仿真,并尝试预测未来一天内超短线存在机会,实验结果验证了股价预测模型的可行性。
The back - propagation algorithm suffers from the problem of slow learning speed and a tendency to get stuck in local minima. In order to overcome these disadvantages, a hybrid of genctic and back - propagation algorithms based on the predictability of stock market for stock price prediction is presented,and a neural network dealing model is developed. Using a sample stock （SA） in closing prices and major indices of stock market for simulating prediction, it is expected to forecast the dealing opportunity of the next day, Experimental resuits verify the feasibility of the prediction model.
出处
《武汉理工大学学报（信息与管理工程版）》
CAS
2006年第11期160-163,共4页
Journal of Wuhan University of Technology：Information & Management Engineering
基金
湖北省自然科学基金资助项目(2002AB041)
关键词
遗传算法
神经网络
BP算法
股市预测
genetic algorithm
neural netwouk
BP algorithm
stock price prediction
作者简介
欧阳林群（1971-）。男，福建浦城人，武汉理工大学信息工程学院硕士研究生。
