Ran Xiangdong, Shan Zhiguang, Fan Yukang, Gao Lei
Beijing Information Technology College, Beijing, China.
Informatization and Industry Research Department, State Information Center, Beijing, China.
PeerJ Comput Sci. 2024 Sep 23;10:e2326. doi: 10.7717/peerj-cs.2326. eCollection 2024.
Stock market is a complex system characterized by collective activity, where interdependencies between stocks have a significant influence on stock price trends. It is widely believed that modeling these dependencies can improve the accuracy of stock trend prediction and enable investors to earn more stable profits. However, these dependencies are not directly observable and need to be analyzed from stock data. In this paper, we propose a model based on Long short-term memory (LSTM) and graph convolutional network to capture these dependencies for stock trend prediction. Specifically, an LSTM is employed to extract the stock features, with all hidden state outputs utilized to construct the graph nodes. Subsequently, Pearson correlation coefficient is used to organize the stock features into a graph structure. Finally, a graph convolutional network is applied to extract the relevant features for accurate stock trend prediction. Experiments based on China A50 stocks demonstrate that our proposed model outperforms baseline methods in terms of prediction performance and trading backtest returns. In trading backtest, we have identified a set of effective trading strategies as part of the trading plan. Based on China A50 stocks, our proposed model shows promising results in generating desirable returns during both upward and downward channels of the stock market. The proposed model has proven beneficial for investors to seeking optimal timing and pricing when dealing with shares.
股票市场是一个以集体活动为特征的复杂系统，其中股票之间的相互依存关系对股价趋势有重大影响。人们普遍认为，对这些依存关系进行建模可以提高股票趋势预测的准确性，并使投资者获得更稳定的利润。然而，这些依存关系无法直接观察到，需要从股票数据中进行分析。在本文中，我们提出了一种基于长短期记忆（LSTM）和图卷积网络的模型，用于捕捉这些依存关系以进行股票趋势预测。具体来说，使用LSTM提取股票特征，将所有隐藏状态输出用于构建图节点。随后，使用皮尔逊相关系数将股票特征组织成图结构。最后，应用图卷积网络提取相关特征以进行准确的股票趋势预测。基于中国A50股票的实验表明，我们提出的模型在预测性能和交易回测回报方面优于基线方法。在交易回测中，我们确定了一组有效的交易策略作为交易计划的一部分。基于中国A50股票，我们提出的模型在股票市场的上涨和下跌通道中都显示出在产生理想回报方面的良好结果。所提出的模型已证明对投资者在处理股票时寻求最佳时机和定价是有益的。
