[论文解读] Exploring Graph Neural Networks for Stock Market Predictions with Rolling Window Analysis

Daiki Matsunaga, Toyotaro Suzumura+1 more|arXiv (Cornell University)|Sep 23, 2019

Stock Market Forecasting Methods被引用 57

一句话总结

本论文评估使用公司知识图谱的图神经网络来预测日经225股票价格，采用滚动窗口回测与LSTM及基准对比，所有模型均有显著提升，且在某些关系类型上表现突出。

ABSTRACT

Recently, there has been a surge of interest in the use of machine learning to help aid in the accurate predictions of financial markets. Despite the exciting advances in this cross-section of finance and AI, many of the current approaches are limited to using technical analysis to capture historical trends of each stock price and thus limited to certain experimental setups to obtain good prediction results. On the other hand, professional investors additionally use their rich knowledge of inter-market and inter-company relations to map the connectivity of companies and events, and use this map to make better market predictions. For instance, they would predict the movement of a certain company's stock price based not only on its former stock price trends but also on the performance of its suppliers or customers, the overall industry, macroeconomic factors and trade policies. This paper investigates the effectiveness of work at the intersection of market predictions and graph neural networks, which hold the potential to mimic the ways in which investors make decisions by incorporating company knowledge graphs directly into the predictive model. The main goal of this work is to test the validity of this approach across different markets and longer time horizons for backtesting using rolling window analysis. In this work, we concentrate on the prediction of individual stock prices in the Japanese Nikkei 225 market over a period of roughly 20 years. For the knowledge graph, we use the Nikkei Value Search data, which is a rich dataset showing mainly supplier relations among Japanese and foreign companies. Our preliminary results show a 29.5% increase and a 2.2-fold increase in the return ratio and Sharpe ratio, respectively, when compared to the market benchmark, as well as a 6.32% increase and 1.3-fold increase, respectively, compared to the baseline LSTM model.

研究动机与目标

• 动机：在股票预测中使用知识图谱来捕捉公司间和市场间的关系。
• 评估图神经网络在跨市场和长期时间范围内通过滚动窗口回测的泛化能力。
• 评估不同知识图谱关系类型对股票价格预测性能的影响。
• 研究用于未来收益回归的时序图神经网络的端到端训练。

提出的方法

• 使用基于历史价格数据通过 LSTM 处理得到的节点特征的图卷积网络（GCN）。
• 通过基于点积的关系强度对邻居贡献进行加权来引入时序动态性（Equations 3）。
• 从一阶和二阶公司关系（供应商、客户、合作伙伴、股东、同业、同客户、同供应商）构建七个邻接矩阵，并测试一个 all-types 邻接 A（K 种关系类型）。
• 应用滚动窗口分析（训练 2000 时间步，测试 200 时间步，滑动窗口）进行约 20 年数据的回测。
• 端到端训练，联合优化 RNN（LSTM）和时序图卷积层，并配以最终回归头。
• 使用年度收益率和 Sharpe 比率，与 Buy-Hold 和基线进行对比来评估性能。

实验结果

研究问题

• RQ1 在跨市场和更长时间范围的股票预测中，基于公司关系的知识图谱数据是否有用？
• RQ2 具有动态关系强度的时序图卷积是否比静态图在预测性能上有提升？
• RQ3 在日经225背景下，哪些关系类型（如 customer-of、supplier-of、common-supplier）最能提高预测准确性？
• RQ4 在滚动窗口上，RNN + GCN 的端到端训练是否能超越标准的 LSTM 和市场基准？

主要发现

• 所有基于图的模型在 Return Ratio 和 Sharpe Ratio 上都优于 Buy-Hold 基准。
• 在测试的图中，all-relations 图获得最佳性能（Return Ratio 29.95%，Sharpe 0.37）。
• customer-of 关系独立提升预测（Return 27.52%，Sharpe 0.35），在某些指标上超过 LSTM。
• 在日经225数据上，LSTM 在 Sharpe 和收益方面被某些图类型（如 customer-of、all）超越。
• 二阶及多关系图有助于缓解稀疏性并在长时期范围内提升泛化能力。