arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2303.16532cs.LGq-fin.STstat.AP
收藏

基于异构持续图神经网络的期货量化投资

Futures Quantitative Investment with Heterogeneous Continual Graph Neural Network

Southwestern University of Finance and Economics(西南财经大学);Macau University of Science and Technology(澳门科技大学);The University of Hong Kong(香港大学)

Min Hu, Zhizhong Tan, Bin Liu, Guosheng Yin

AI总结:

针对高频交易期货价格预测难题,提出融合多因子定价理论与时空图神经网络的异构持续学习因子预测器,通过三项异构任务捕捉多周期趋势,用互信息缓解灾难性遗忘,在49个中国商品期货上预测精度优于现有模型,为交易决策提供依据。

摘要:

本研究旨在解决高频交易(HFT)中的期货价格预测挑战,提出了一种基于图神经网络的持续学习因子预测器。该模型将多因子定价理论与实时市场动态相结合,有效规避了现有方法缺乏金融理论指导、忽略各类趋势信号及其相互作用的局限性。我们提出了三项异构任务,包括价格移动平均回归、价格缺口回归和变点检测,以追踪数据中存在的短期、中期和长期趋势因子。此外,本研究还考虑了期货合约的截面相关性特征——不同期货的价格往往表现出强烈的动态相关性。每个变量(期货合约)不仅依赖于其自身的历史值(时间维度),还依赖于对其他变量的观测(截面维度)。为了更准确地捕捉这些动态关系,我们借助时空图神经网络(STGNN)来增强模型的预测能力。该模型采用持续学习策略,同时兼顾这些任务(因子)。此外,由于任务的异构性,我们提出利用原始观测值与提取特征之间的互信息来计算参数重要性,以缓解灾难性遗忘(CF)问题。在中国期货市场的49个商品期货上进行的实证测试表明,所提出的模型在预测精度方面优于其他最先进的模型。本研究不仅推动了金融理论与深度学习的融合,还为实际交易决策提供了科学依据。

英文摘要:

This study aims to address the challenges of futures price prediction in high-frequency trading (HFT) by proposing a continuous learning factor predictor based on graph neural networks. The model integrates multi-factor pricing theories with real-time market dynamics, effectively bypassing the limitations of existing methods that lack financial theory guidance and ignore various trend signals and their interactions. We propose three heterogeneous tasks, including price moving average regression, price gap regression and change-point detection to trace the short-, intermediate-, and long-term trend factors present in the data. In addition, this study also considers the cross-sectional correlation characteristics of future contracts, where prices of different futures often show strong dynamic correlations. Each variable (future contract) depends not only on its historical values (temporal) but also on the observation of other variables (cross-sectional). To capture these dynamic relationships more accurately, we resort to the spatio-temporal graph neural network (STGNN) to enhance the predictive power of the model. The model employs a continuous learning strategy to simultaneously consider these tasks (factors). Additionally, due to the heterogeneity of the tasks, we propose to calculate parameter importance with mutual information between original observations and the extracted features to mitigate the catastrophic forgetting (CF) problem. Empirical tests on 49 commodity futures in China's futures market demonstrate that the proposed model outperforms other state-of-the-art models in terms of prediction accuracy. Not only does this research promote the integration of financial theory and deep learning, but it also provides a scientific basis for actual trading decisions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑