基于神经网络技术的股票频谱分析

来源期刊:中南大学学报(自然科学版)2011年第3期

论文作者:李清峰 彭文峰 何静

文章页码:726 - 730

关键词:波浪理论;费波纳奇数列;频谱分析;神经网络

Key words:stock wave theory; Fibonacci array; frequency analysis; artificial neural network

摘    要:根据艾略特波浪理论以及波浪理论中的各参数具有费波纳奇数列关系的特征,分析股票价格波形的特点;运用人工神经网络模型,提出基于波形分解与重构的神经网络预测方法,给出具体的实现过程。研究结果表明:通过波形分解与重构,把原始价格时间序列分解为规律相对简单、不同频率范围内的子波动序列来提高神经网络的预测精度,实现对特征不同的信号选取不同的参数模型进行预测;采用傅里叶反变换拟合出股价波动变化趋势的曲线,以达到预测股价波动变化周期的目的。

Abstract: According to Elliott wave theory and wave theory of the Fibonacci array, the stock price profile characteristics were analyzed. The neural network was researched and a neural network prediction method was brought out. Its concrete realization process based on wavelet decomposition and reconstruction were made. The results show that through this method, the price function is decomposed into a series of wavelets in different frequency ranges, whose fluctuation rule can be easily grasped. This method increases the neural network prediction precision, and makes it possible to predict signals with prediction models of different parameters. The inverse Fourier transform can be used to fit the stock price fluctuation change tendency, and to forecast stock price fluctuation cycle.

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号