基于双流LSTM神经网络的股价趋势预测

doi:10.3969/j.issn.0255-8297.2023.02.013

应用科学学报 ›› 2023, Vol. 41 ›› Issue (2): 344-358.doi: 10.3969/j.issn.0255-8297.2023.02.013

基于双流LSTM神经网络的股价趋势预测

吴峰¹, 谢聪², 姬少培³

1. 南宁师范大学师园学院经济管理系, 广西南宁 530226;
2. 广西农业职业技术大学信息工程学院, 广西南宁 530005;
3. 中国电子科技集团公司第三十研究所, 四川成都 610041

收稿日期:2021-07-08 出版日期:2023-03-31 发布日期:2023-03-29
通信作者: 谢聪,教授,研究方向为机器学习、智能算法。E-mail:435323646@qq.com E-mail:435323646@qq.com
基金资助:
国家自然科学基金企业创新发展联合基金（No.U19B2021）；广西高等教育本科教学改革工程项目（No.2021JGA425）；广西中青年教师科研基础能力提升项目（No.2021KY1736,No.2021KY1731）；广西高校中青年教师科研基础能力提升项目（No.2022KY1643）资助

Stock Price Trend Prediction Based on Dual-Stream LSTM Neural Network

WU Feng¹, XIE Cong², JI Shaopei³

1. Department of Economic Management, Shiyuan College of Nanning Normal University, Nanning 530226, Guangxi, China;
2. College of Information Engineering, Guangxi Vocational University of Agriculture, Nanning 530005, Guangxi, China;
3. The 30 th Research Institute of China Electronics Technology Group Corporation, Chengdu 610041, Sichuan, China

Received:2021-07-08 Online:2023-03-31 Published:2023-03-29

摘要/Abstract

摘要： 股价波动研究依赖分析金融新闻数据集浅层特征，而忽略了金融新闻句子中单词之间的结构关系，从而导致股价波动预测研究效果不佳。针对该问题，提出了一种基于双流长短时记忆网络（long short term memory network,LSTM）神经网络的股价趋势预测模型（Sent2Vec-DLSTM）。该模型的创新之处在于：提出了基于金融股票新闻数据集和哈佛IV-4情绪词典训练的情感词向量生成模型——Sent2Vec；提出了新型的双流LSTM神经网络（Dual-stream LSTM,DLSTM）。在实验中，首先用标普500指数历史数据以及爬取获得的金融类文章进行标普500指数的趋势预测，然后用VietStock新闻和来自Cophieu68的股票价格数据预测VN指数的变化趋势。结果表明，Sent2Vec-DLSTM相较于现有模型在股价趋势预测中具有更好的效果。

关键词: 金融新闻, 双流长短时记忆网络, 情感词嵌入, 股价趋势预测, 情感分析

Abstract: Previous research on stock price volatility prediction relies on analyzing shallow features of financial news datasets and ignores the structural relationship between words in financial news, resulting in poor prediction performance. Aiming at this problem, we propose a stock price trend prediction model (Sent2Vec-DLSTM) based on a dual-stream long short-term memory network (LSTM) neural network. A vector generation model of emotional words called Sent2Vec is first proposed based on financial stock news data set and Harvard IV-4 emotion dictionary training, which is then combined with dual-stream LSTM neural network (DLSTM). In the experiment, the historical data of the S&P 500 index and the financial articles obtained by crawling are used to predict the trend of the S&P 500 index. the VietStock news and stock price data from cophieu68 are then used to predict the trend of the VN index. The results show that Sent2Vec-DLSTM outperforms existing models in stock price trend prediction.

Key words: financial news, dual-stream long short-term memory (LSTM) network, emotional word embedding, stock price trend prediction, sentiment analysis

中图分类号:

TP301

吴峰, 谢聪, 姬少培. 基于双流LSTM神经网络的股价趋势预测[J]. 应用科学学报, 2023, 41(2): 344-358.

WU Feng, XIE Cong, JI Shaopei. Stock Price Trend Prediction Based on Dual-Stream LSTM Neural Network[J]. Journal of Applied Sciences, 2023, 41(2): 344-358.

参考文献

[1] 邓飞燕, 岑少琪, 钟凤琪, 等. 基于LSTM神经网络的短期价格趋势预测[J]. 计算机系统应用, 2021, 30(4):187-192. Deng F Y, Cen S Q, Zhong F Q, et al. Short-term price trend forecast based on LSTM neural network[J]. Computer Systems & Applications, 2021, 30(4):187-192. (in Chinese)
[2] 张冰, 王传美, 贺素香. 改进的TSVR模型在股市高频数据上的预测[J]. 计算机工程与设计, 2019, 40(11):3241-3246. Zhang B, Wang C M, He S X. Prediction of improved TSVR model on high frequency stock market[J]. Computer Engineering and Design, 2019, 40(11):3241-3246. (in Chinese)
[3] 刘玉敏, 李洋, 赵哲耘. 基于特征选择的RF-LSTM模型成分股价格趋势预测[J]. 统计与决策, 2021, 37(1):157-160. Liu Y M, Li Y, Zhao Z Y. Price trend prediction of RF-LSTM model based on feature selection[J]. Statistics and Decision-Making, 2021, 37(1):157-160. (in Chinese)
[4] 裴曼如, 张立文. 基于投资者情绪和深度学习的股票价格趋势预测研究[J]. 金融发展, 2020(1):78-97. Pei M R, Zhang L W. Research on stock price trend prediction based on investor sentiment and deep learning[J]. Financial Development, 2020(1):78-97. (in Chinese)
[5] Chong E, Han C, Park F C. Deep learning networks for stock market analysis and prediction:methodology, data representations, and case studies[J]. Expert Systems with Applications, 2017, 83:187-205.
[6] Weng B, Ahmed M A, Megahed F M. Stock market one-day ahead movement prediction using disparate data sources[J]. Expert Systems with Applications, 2017, 79:153-163.
[7] 陈嘉. 基于深度学习的语音情感识别[D]. 南京:南京邮电大学, 2019.
[8] 张明月, 王静. 基于深度学习的交互似然目标跟踪算法[J]. 计算机科学, 2019, 46(2):279-285. Zhang M Y, Wang J. Interactive likelihood target tracking algorithm based on deep learning[J]. Computer Science, 2019, 46(2):279-285. (in Chinese)
[9] 张珂, 冯晓晗, 郭玉荣, 等. 图像分类的深度卷积神经网络模型综述[J]. 中国图象图形学报, 2021, 26(10):2305-2325. Zhang K, Feng X H, Guo Y R, et al. Overview of deep convolutional neural networks models for image classification[J]. Journal of Image and Graphics, 2021, 26(10):2305-2325. (in Chinese)
[10] Chen J Y, Zheng H B, Xiong H, et al. FineFool:a novel DNN object contour attack on image recognition based on the attention perturbation adversarial technique[J]. Computers & Security, 2021, 104:102220.
[11] 张柏翰, 凌捷. 改进的基于DNN的恶意软件检测方法[J]. 计算机工程与应用, 2021, 57(10):81-87. Zhang B H, Ling J. Improved malware detection method based on DNN[J]. Computer Engineering and Applications, 2021, 57(10):81-87. (in Chinese)
[12] Basiri M E, Nemati S, Abdar M, et al. ABCDM:an attention-based bidirectional CNNRNN deep model for sentiment analysis[J]. Future Generation Computer Systems, 2021, 115:279-294.
[13] 姬少培. 基于深度LSTM神经网络的软件可靠性预测[D]. 哈尔滨:哈尔滨工程大学, 2018.
[14] 穆凯代姆罕·伊敏江, 艾斯卡尔·艾木都拉, 米吉提·阿不里米提. 基于CNN-HMM和RNN的维吾尔语语音识别[J]. 现代电子技术, 2021, 44(11):172-176. Mukaddam I, Askar H, Mijit A. Uyghur speech recognition based on CNN-HMM and RNN[J]. Modern Electronic Technology, 2021, 44(11):172-176. (in Chinese)
[15] Dang M, Duong D. Improvement methods for stock market prediction using financial news articles[C]//20163rd National Foundation for Science and Technology Development Conference on Information and Computer Science (NICS). IEEE, 2016.
[16] Oueslati O, Cambria E, Hajhmida M B, et al. A review of sentiment analysis research in Arabic language[J]. Future Generation Computer Systems, 2020, 112:408-430.
[17] 邬明强, 邬佳明, 辛伟彬. Word2Vec+LSTM多类别情感分类算法优化[J]. 计算机系统应用, 2020, 29(1):130-136. Wu M Q, Wu J M, Xin W B. Optimization of Word2Vec+LSTM multi-category sentiment classification algorithm[J]. Computer System & Application, 2020, 29(1):130-136. (in Chinese)
[18] 孟仕林. 基于情感信息融合的情感分析方法研究[D]. 南京:南京航空航天大学, 2020.

基于双流LSTM神经网络的股价趋势预测

Stock Price Trend Prediction Based on Dual-Stream LSTM Neural Network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价