《计算机应用》唯一官方网站 ›› 2022, Vol. 42 ›› Issue (5): 1624-1633.DOI: 10.11772/j.issn.1001-9081.2021030519

• 前沿与综合应用 • 上一篇    下一篇

基于改进遗传算法和图神经网络的股市波动预测方法

李晓寒(), 贾华丁, 程雪, 李太勇   

  1. 西南财经大学 经济信息工程学院,成都 611130
  • 收稿日期:2021-04-06 修回日期:2021-07-15 接受日期:2021-07-15 发布日期:2022-06-11 出版日期:2022-05-10
  • 通讯作者: 李晓寒
  • 作者简介:李晓寒(1985—),男,山东济南人,博士研究生,CCF会员,主要研究方向:金融信息管理、智能决策、大数据、商务智能 lixiaohan134@163.com
    贾华丁(1956—),男,四川成都人,教授,博士,CCF会员,主要研究方向:机器学习、算法交易、扩频序列设计
    程雪(1997—),女,山西河津人,硕士研究生,CCF会员,主要研究方向:机器学习、量化交易
    李太勇(1979—),男,四川安岳人,教授,博士,CCF高级会员,主要研究方向:机器学习、模式识别、自然计算。
  • 基金资助:
    中央高校基本科研业务费专项资金资助项目(JBK2102001)

Stock market volatility prediction method based on improved genetic algorithm and graph neural network

Xiaohan LI(), Huading JIA, Xue CHENG, Taiyong LI   

  1. School of Economic Information Engineering,Southwestern University of Finance and Economics,Chengdu Sichuan 611130,China
  • Received:2021-04-06 Revised:2021-07-15 Accepted:2021-07-15 Online:2022-06-11 Published:2022-05-10
  • Contact: Xiaohan LI
  • About author:LI Xiaohan, born in 1985,Ph. D. candidate. His research interestsinclude financial information management,intelligent decision-making,big data,business intelligence.
    JIA Huading, born in 1956,Ph. D.,professor. His researchinterests include machine learning,algorithmic trading,spread spectrum sequence design.
    CHENG Xue, born in 1997, M. S. candidate. Her researchinterests include machine learning,quantitative trading.
    LI Taiyong, born in 1979, Ph. D., professor. His researchinterests include machine learning, pattern recognition, naturalcomputing.
  • Supported by:
    Fundamental Research Funds for Central Universities(JBK2102001)

摘要:

针对支持向量机(SVM)、长短期记忆(LSTM)网络等智能算法在股市波动预测过程中股票评价特征选择困难及时序关系维度特征缺失的问题,为能够准确预测股票波动、有效防范金融市场风险,提出了一种基于改进遗传算法(IGA)和图神经网络(GNN)的股市波动预测方法——IGA-GNN。首先,利用相邻交易日间的时序关系构建股市交易指标图数据;其次,通过评价指标特性优化交叉、变异概率来改进遗传算法(GA),从而实现节点特征选择;然后,建立图数据的边与节点特征的权重矩阵;最后,运用GNN进行图数据节点的聚合与分类,实现了股市波动预测。在实验阶段,所研究的股票总评价指标数为130个,其中IGA在GNN方法下提取的有效评价指标87个,使指标数量降低了33.08%。应用所提IGA在智能算法中进行特征提取,得到的算法与未进行特征提取的智能算法相比,预测准确率整体提升了7.38个百分点;而与应用传统GA进行智能算法的特征提取相比,应用所提IGA进行智能算法的特征提取的总训练时间缩短了17.97%。其中,IGA-GNN方法的预测准确率最高,相较未进行特征提取的GNN方法的预测准确率整体提高了19.62个百分点;而该方法与用传统GA进行特征提取的GNN方法相比,训练时间平均缩短了15.97%。实验结果表明,所提方法可对股票特征进行有效提取,预测效果较好。

关键词: 股市预测, 遗传算法, 图神经网络, 机器学习, 特征选择

Abstract:

Aiming at the difficulty in selecting stock valuation features and the lack of time series relational dimension features during the prediction of stock market volatility by intelligent algorithms such as Support Vector Machine (SVM) and Long Short-Term Memory (LSTM) network, in order to accurately predict stock volatility and effectively prevent financial market risks, a new stock market volatility prediction method based on Improved Genetic Algorithm (IGA) and Graph Neural Network (GNN) named IGA-GNN was proposed. Firstly, the data of stock market trading index graph was constructed based on the time series relation between adjacent trading days. Secondly, the characteristics of evaluation indexes were used to improve Genetic Algorithm (GA) by optimizing crossover and mutation probabilities, thereby realizing the node feature selection. Then, the weight matrix of edge and node features of graph data was established. Finally, the GNN was used for the aggregation and classification of graph data nodes, and the stock market volatility prediction was realized. In the experiment stage, the studied number of total evaluation indexes of stock was 130, and 87 effective evaluation indexes were extracted from the above by IGA under GNN method, making the number of stock evaluation indexes reduced by 33.08%. The proposed IGA was applied to the intelligent algorithms for feature extraction. The obtained algorithms has the overall prediction accuracy improved by 7.38 percentage points compared with the intelligent algorithms without feature extraction. Compared with applying the traditional GA for feature extraction of the intelligent algorithms, applying the proposed IGA for feature extraction of the intelligent algorithms has the total training time shortened by 17.97%. Among them, the prediction accuracy of IGA-GNN method is the highest, which is 19.62 percentage points higher than that of GNN method without feature extraction. Compared with the GNN method applying the traditional GA for feature extraction, the IGA-GNN method has the training time shortened by 15.97% on average. Experimental results show that, the proposed method can effectively extract stock features and has good prediction effect.

Key words: stock market prediction, Genetic Algorithm (GA), Graph Neural Network (GNN), machine learning, feature selection

中图分类号: