摘要
探讨神经网络理论的辨识特性 ,基于先验信息对股票市场建立非线性动态模型 ,用以预报市场短期走向。通过实证分析表明 ,采用神经网络所建立的股票市场模型能反映一段时间内市场平稳运行规律 ,对次日的市场行情变化预报的准确率较高 ,对市场短期预报有一定的参考价值。
This paper discusses the characteristies of neural net-Works which is suitable to identify the non-linear dynamic model of stock market and estimate its tendancy on the basis of prior information.The result shows that the model of stock market can reveal the market stable running laws for a period and forecast the market change the next day.It's also helpful to forecast the short-term market.
出处
《湖南工程学院学报（自然科学版）》
2002年第2期51-53,60,共4页
Journal of Hunan Institute of Engineering(Natural Science Edition)
关键词
神经网络
股市
建模
非线性模型
市场预报
stock market
non-linear model
market forecast
neural net-works
