节点文献

基于人工神经元网络的股票分析及其逻辑设计

Stock Analyse and Its Logical Design Based on Artificial Neural Network

【作者】 温渤

【导师】 赵金楼;

【作者基本信息】 哈尔滨工程大学 , 产业经济学, 2003, 硕士

【摘要】 股票市场具有高收益性与高风险性并存的特点。为趋利避害投资者们一直孜孜以求探索其内在规律,寻找有效的分析方法和工具。近年来,计算机技术与人工智能的发展为投资者更加科学地、定量地分析股票市场,测评股票投资价值提供了有利条件。本论文正是在这一背景下,就利用人工神经元网络技术分析股票市场进行了初步研究。 论文首先阐述了股票分析的传统理论及其存在的优缺点,接着阐述了人工神经元网络的基本理论,表明了利用人工神经元网络对股票市场进行分析的优点所在。 其次,建立了神经网络股票分析模型。模型主要由三部分组成:基于上市公司财务报表数据、公司股票实时基础数据、国家宏观经济指标数据建立的神经网络股票分析指标体系;算法模型选择与网络配置;模型输出。 再次,依据上述模型构建的思想,论文对该模型软件实现进行了逻辑设计,着重论述了软件实现时的系统功能结构设计、系统数据流程、网络学习过程设计等关键性问题,为模型最终实现计算机化应用打下了良好的基础。 最后,论文选取2002年6月份沪市浦发银行、民生银行、爱建股份三只股票真实数据进行了实证分析。实证分析的结果表明论文所建立的基于人工神经元网络的股票分析模型具有一定的理论价值与应用价值。

【Abstract】 High income with high risk is the character of the stock market. At all times investors work hardly to grope after the rule of the stock market for gainning the earnings and avoiding the loss. In the lately years, the development of the computer technology and artificial intelligence provides with the favorable environment to scientific analyze the stock market and measure stock value for the investors. The thesis starts to research the stock market with neural network technology under the ground of these conditions.Firstly, the article clarifies the traditional theory of the stock analyse with its merits and demerits. And then ,the article clarifies the basic theory of the neural network which points out the merit of using neural network to analyze the stock market.Secondly, in the article the neural stock analyse model has been constituted .The model is made of three parts: index system based on the finance report data synchronous dada of the stock market and the macro-economy data of the country; the choice of the arithmetic model; output of the model.Thirdly, according to the model idea, the thesis emphatically discusses the key questions such as the system function, the system data flow diagram. And these finally build the favorable foundation to realize the model.Finally, the thesis makes the positive analyse with the real stock data of Pufa, Minsheng, Aijian. The results of the positive analyse demonstrates that the neural stock analyse model that established in the thesis has the sectional theory value and application value.

【关键词】 神经网络股票分析逻辑设计
【Key words】 Neural networkStock analyseLogical design
  • 【分类号】F830.91
  • 【被引频次】2
  • 【下载频次】538
节点文献中: 

本文链接的文献网络图示:

本文的引文网络