EP-GAT: Energy-based Parallel Graph Attention Neural Network for Stock Trend Classification
This addresses stock movement prediction for financial analysts, offering an incremental improvement over existing graph neural network methods by better capturing dynamic and hierarchical features.
The paper tackles stock trend classification by proposing EP-GAT, which uses an energy-based dynamic graph and parallel attention to model inter-stock dependencies and intra-stock dynamics, achieving consistent outperformance over five baselines across multiple datasets.
Graph neural networks have shown remarkable performance in forecasting stock movements, which arises from learning complex inter-dependencies between stocks and intra-dynamics of stocks. Existing approaches based on graph neural networks typically rely on static or manually defined factors to model changing inter-dependencies between stocks. Furthermore, these works often struggle to preserve hierarchical features within stocks. To bridge these gaps, this work presents the Energy-based Parallel Graph Attention Neural Network, a novel approach for predicting future movements for multiple stocks. First, it generates a dynamic stock graph with the energy difference between stocks and Boltzmann distribution, capturing evolving inter-dependencies between stocks. Then, a parallel graph attention mechanism is proposed to preserve the hierarchical intra-stock dynamics. Extensive experiments on five real-world datasets are conducted to validate the proposed approach, spanning from the US stock markets (NASDAQ, NYSE, SP) and UK stock markets (FTSE, LSE). The experimental results demonstrate that EP-GAT consistently outperforms competitive five baselines on test periods across various metrics. The ablation studies and hyperparameter sensitivity analysis further validate the effectiveness of each module in the proposed method.