基于BP神经网络和GARCH模型的中国银行股票价格预测实证分析

兰州大学机构库 >数学与统计学院

	基于BP神经网络和GARCH模型的中国银行股票价格预测实证分析
Alternative Title	The bank of China stock price forecast empirical analysis Based on BP neural network and GARCH model
	林楠
Thesis Advisor	严定琪
	2014-05-31
Degree Grantor	兰州大学
Place of Conferral	兰州
Degree Name	硕士
Keyword	BP神经网络 GARCH模型短期预测
Abstract	随着中国金融市场与国际接轨,金融衍生品市场初步建成,金融投资工具在多样化、高杠杆的条件下也带来了巨大的金融风险.复杂多变的金融市场上对于金融投资分析工具的要求也就更高,催生出了多种对于股票价格预测的方法.对于不同的数据以及不同的市场环境需要不同分析方法.神经网络算法所具有的分布式存储数据以及学习反馈机制的特点使得它在预测等方面有独到的作用.本文中选取中国银行股票收盘价,采用BP神经网络（即前馈模型）和GARCH模型的方法对股票价格进行了预测,通过对比分析得出结论BP神经网络在隐含层节点数为5时对于市场数据拟合度最好;而GARCH模型在对股票价格预测方面也是有效的,主要是因为中国银行股票数据具有尖峰厚尾和平稳性特征.最终得出结论两种预测方法都能够对中国银行股票短期价格进行预测,但BP神经网络预测方法优于GARCH模型的预测方法.
Other Abstract	With China's financial market in line with international standards, the financial derivatives market set up, financial instruments under the condition of diversified high leverage also poses a huge financial risk. Complex financial market to the requirement of financial investment analysis tools are higher, spawned a variety of ways to for stock price prediction.. For different data and different market environment requires a different analysis methods. Neural network algorithm of distributed data storage, and the characteristics of the learning feedback mechanism makes it have a unique role in prediction, etc. This article select the stock's closing price of the bank of China, using the BP neural network (feedforward model) and GARCH model to forecast the stock price of, through the comparison and analysis concluded that BP neural network in the number of hidden layer nodes is 5 for market data fitting is best. And GARCH model is effective in of stock price forecasting, mainly because of the bank of China shares data with rush thick tail and stability characteristics. Finally concluded two forecasting methods are able to predict short-term stock price and the bank of China but the BP neural network prediction method is superior to the GARCH model prediction method.
URL	查看原文
Language	中文
Document Type	学位论文
Identifier	https://ir.lzu.edu.cn/handle/262010/225254
Collection	数学与统计学院
Recommended Citation GB/T 7714	林楠. 基于BP神经网络和GARCH模型的中国银行股票价格预测实证分析[D]. 兰州. 兰州大学,2014.

Files in This Item:
There are no files associated with this item.

If you have any objections to this item, please fill out the form below and the administrator will contact you as soon as possible.
Content:
Email：	*
Institution:
Verification Code:	Refresh

Any comments and suggestions are welcomed.
Title:	*
Content:
Email：	*
Verification Code:	Refresh

数学与统计学院知识库