Paper: arXiv 2303.16532

Authors: Min Hu, Zhizhong Tan, Bin Liu, Guosheng Yin

Abstract

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.

Complexity vs Empirical Score

  • Math Complexity: 7.0/10
  • Empirical Rigor: 6.0/10 (capped from 7.5: transaction costs only partially modelled; see penalty flags)
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper presents an innovative integration of spatio-temporal graph neural networks (STGNN) and continual learning to solve catastrophic forgetting in multi-task futures prediction. The methodology is mathematically well-grounded via mutual information feature weighting, and the empirical evaluation across 49 Chinese commodity futures demonstrates robust outperformance.

Research Flowchart

  flowchart TD
    A[Research Goal: Improve High-Frequency Futures Prediction via Continual STGNN] --> B[Data Input: High-Frequency Data for 49 Chinese Commodity Futures]
    
    subgraph Methodology & Processing
        B --> C[Heterogeneous Multi-Task Learning: Price MA, Price Gap & Change-Point Detection]
        C --> D[Spatio-Temporal GNN: Captures Temporal Trends & Cross-Sectional Correlations]
        D --> E[Continual Learning with Mutual Information: Prevents Catastrophic Forgetting]
    end
    
    E --> F[Empirical Evaluation: Tested Against State-of-the-Art Baselines]
    F --> G[Key Outcomes: Outperforms Baselines in Accuracy & Validates Financial Theory Integration]