MATLAB基于BP神经网络的股票价格预测研究
时间:2017-06-11 22:28 来源:毕业论文 作者:毕业论文 点击:次
| 摘要股票市场在金融投资领域中占有重要地位，随着社会经济的发展和人们投资意识的增强，股票投资已成为众多个人理财的重要方式之一。然而，股票市场高风险和高收益并存，具有高度的非线性，而且原始数据波动较大，随机性强。因此，如何建立一个运算速度和精度都较高的股市预测模型，对于投资者具有理论意义和实际运用价值。 BP神经网络模型具有非线性映射，能以任意精度逼近函数关系，容错能力大，学习能力即自适应能力强等特点，能在一定的精度范围内实现良好的模拟。跟其它预测模型相比，它的有点在于它能不追溯数据产生原因，通过给定的训练样本进行机械训练，建立输出与输入变量之间的函数关系，建立非线性过程的模拟模型。因此，利用神经网络模型来进行股价预测是比较适合的。 本论文根据BP神经网络进行股票预测，采用改进后的BP算法进行股市预测，并通过MATLAB软件进行股票价格预测进行仿真。以深发展A为例，对其所建立的模型进行训练并预测，达到了良好的预测效果。10114 关键词 股票预测 BP神经网络 MATLAB仿真 Levenberg-Marquardt算法 毕 业 论 文 外 文 摘 要 Title The study of stock price prediction based on Neutral Network Abstract The stock market plays an important role in financial investment. With the economic growth and the conversion of people’s investment, stock has become an important part of people's life in modern time. However, the proceeds of stock investment always equal the risk, and the stock market is a very complex nonlinear dynamic system. The data of short-term is always discontinuity and shakes heavily with randomicity. Establishing a stock forecasting model, which has higher operation rate and precisian, has theoretical significance and applicable value. The BPNN model has many merits such as nonlinear-mapping, getting approach to any function by any precision, strong ability of fault-tolerant, good at learning and better adaptiveness. In theory, it can be simulated within a certain range of accuracy of any nonlinear continuous function. The novelty of artificial neural network is that without understanding the cause of data, through the given training samples for machine training, we can establish the output and input variables of the function, and simulate the nonlinear process modeling. Using neutral network to forecast stock price is very appropriate. According to the principle of stock prediction based on BP network, the stock is predicted by adopting improved BP algorithm and simulation experiments are conducted through MATLAB. At last, taking the stock price of 000001 for example, the established prediction model is trained and then its stock data are predicted using the trained network and good effect has been grained. Keywords stock market forecasting model BP neutral network MATLAB Levenberg-Marquardt Algorithm 目 次 1 绪论 1 1.1 研究背景和意义 1 1.2 文献综述 1 1.3 本文主要的研究内容和手段 4 2 股票价格预测方法简介 6 2.1 股票预测面临的问题 6 2.2 股票预测分析方法 7 3 神经网络及BP算法 10 3.1 人工神经网络 10 3.2 BP神经网络 15 3.3 BP网络的改进 17 4 基于神经网络模型的股票预测 19 4.1 BP网络预测股票的步骤 19 4.2 基于BP的股票预测模型 19 4.3 利用matlab进行分析 20 (责任编辑：qin) |