全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于LSTM模型的股价分析及预测
Analysis and Forecast of Stock Price Based on LSTM Model

DOI: 10.12677/AAM.2022.111010, PP. 65-70

Keywords: Python,长短期记忆网络,股票价格,半导体行业
Python
, Long Short-Term Memory Network, Stock Price, Semiconductor Industry

Full-Text   Cite this paper   Add to My Lib

Abstract:

股价预测一直都是股票投资者重点关注和重点研究的方向。针对股价具有高度非线性、高噪声、动态性等问题,本文采用长短期记忆网络(LSTM)模型对股价进行预测。数据取自半导体行业公司股票价格,采用python深度学习框架构造长短期记忆网络模型,分别对每一组股票的开盘价进行预测,再通过均方误差和决定系数对预测结果进行评价。实验结果表明将LSTM神经网络用于股票价格预测具有较好的效果,可以为投资者提供一定的参考。
Stock price forecasting has always been the focus and research direction of stock investors. Aiming at the problems of high non-linearity, high noise and dynamics in stock prices, this paper uses a long short-term memory network (LSTM) model to predict stock prices. The data is taken from the stock prices of companies in the semiconductor industry, and a long- and short-term memory network model is constructed using the python deep learning framework to predict the opening price of each group of stocks, and then the prediction results are evaluated through the mean square error and the coefficient of determination. The experimental results show that the use of LSTM neural network for stock price prediction has a good effect, and it can provide a certain reference for investors.

References

[1]  张如梦, 张华美. BP神经网络与ARMA-GARCH模型在股票预测中的对比分析[J]. 高师理科学刊, 2021, 41(4): 14-20.
[2]  胡衍坤. 基于TensorFlow进行股票预测的深度学习模型的设计与实现[J]. 计算机应用与软件, 2018, 35(6): 267-271.
[3]  杨琦, 曹显兵. 基于ARMA-GARCH模型的股票价格分析与预测[J]. 数学的实践与认识, 2016, 46(6): 80-86.
[4]  黄颖, 杨会杰. 基于XGBoost和LSTM模型的金融时间序列预测[J]. 科技和产业, 2021, 21(8): 158-162.
[5]  张康林. 基于pytorch的LSTM模型对股价的分析与预测[J]. 计算机技术与发展, 2021, 31(1): 161-167.
[6]  宋刚, 张云峰, 包芳勋. 基于粒子群优化LSTM的股票预测模型[J]. 北京航空航天大学学报, 2019, 45(12): 2533-2542.
[7]  李雄英, 陈小玲, 曾凯华. 基于三类模型的四大银行股票收益率预测研究[J]. 经济数学, 2018, 35(4): 21-27.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133