北京航空航天大学学报 ›› 2019, Vol. 45 ›› Issue (12): 2533-2542.doi: 10.13700/j.bh.1001-5965.2019.0388

• 论文 • 上一篇    下一篇

基于粒子群优化LSTM的股票预测模型

宋刚1,2, 张云峰1,2, 包芳勋3, 秦超1,2   

  1. 1. 山东财经大学 计算机科学与技术学院, 济南 250014;
    2. 山东财经大学 山东省数字媒体技术重点实验室, 济南 250014;
    3. 山东大学 数学学院, 济南 250100
  • 收稿日期:2019-07-10 出版日期:2019-12-20 发布日期:2019-12-31
  • 通讯作者: 张云峰 E-mail:yfzhang@sdufe.edu.cn
  • 作者简介:宋刚 男,硕士研究生。主要研究方向:机器学习、数据分析;张云峰 男,博士,教授,博士生导师。主要研究方向:计算机视觉、数据分析。
  • 基金资助:
    国家自然科学基金(61672018,61772309);国家自然科学基金-浙江两化融合联合基金(U1609218);山东省重点研发计划(2016GSF120013,2017GGX10109,2018GGX101013);山东省高等学校优势学科人才队伍培育计划;山东省自然科学杰出青年(ZR2018JL022);山东省自然科学基金(ZR2019MF051)

Stock prediction model based on particle swarm optimization LSTM

SONG Gang1,2, ZHANG Yunfeng1,2, BAO Fangxun3, QIN Chao1,2   

  1. 1. School of Computer Science and Technology, Shandong University of Finance and Economics, Jinan 250014, China;
    2. Shandong Key Laboratory of Digital Media Technology, Shandong University of Finance and Economics, Jinan 250014, China;
    3. School of Mathematics, Shandong University, Jinan 250100, China
  • Received:2019-07-10 Online:2019-12-20 Published:2019-12-31
  • Supported by:
    National Natural Science Foundation of China (61672018, 61772309); National Natural Science Foundation of China-Zhejiang Two Integration Joint Fund (U1609218); Key Research and Development Project of Shandong Province (2016GSF120013, 2017GGX10109, 2018GGX101013); Fostering Project of Dominant Discipline and Talent Team of Shandong Province Higher Education Institutions; Natural Science Foundation for Excellent Youth of Shandong Province (ZR2018JL022); Natural Science Foundation of Shandong Province (ZR2019MF051)

摘要: 为了提高股票时间序列预测精度,增强预测模型结构参数可解释性,提出一种基于自适应粒子群优化(PSO)的长短期记忆(LSTM)股票价格预测模型(PSO-LSTM),该模型在LSTM模型的基础上进行改进和优化,因此擅长处理具有长期依赖关系的、复杂的非线性问题。通过自适应学习策略的PSO算法对LSTM模型的关键参数进行寻优,使股票数据特征与网络拓扑结构相匹配,提高股票价格预测精度。实验分别以沪市、深市、港股股票数据构建了PSO-LSTM模型,并对该模型的预测结果与其他预测模型进行比较分析。结果表明,基于自适应PSO的LSTM股票价格预测模型不但提高了预测准确度,而且具有普遍适用性。

关键词: 粒子群优化(PSO), LSTM神经网络, 自适应, 股票价格预测, 预测精度

Abstract: This paper proposes a stock price prediction model based on particle swarm optimization long short-term memory (PSO-LSTM). This model improves and optimizes the LSTM model, which makes it more appropriate for analyzing relationships such as long-term dependency and for solving complex nonlinear problems. Through finding the key parameters in LSTM model by the PSO algorithm with adaptive learning strategy, the stock data feature matches the network topology structure, and the model's prediction accuracy of stock price is improved. In the experiment, PSO-LSTM models are constructed respectively based on the stock datasets from Shanghai, Shenzhen and Hong Kong, and then they are compared to other prediction models. The comparison results show that the PSO-LSTM stock price prediction model achieves higher prediction accuracy and has general applicability.

Key words: particle swarm optimization (PSO), LSTM neural network, adaptive, stock price forecast, prediction accuracy

中图分类号: 


版权所有 © 《北京航空航天大学学报》编辑部
通讯地址:北京市海淀区学院路37号 北京航空航天大学学报编辑部 邮编:100191 E-mail:jbuaa@buaa.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发