EP-GAT: Energy-based Parallel Graph Attention Neural Network for Stock Trend Classification

TL;DR

EP-GAT introduces a dynamic, energy-based graph attention model that captures evolving stock inter-dependencies and intra-stock hierarchies, significantly improving stock trend prediction accuracy.

Contribution

It proposes a novel energy-based dynamic graph construction and a parallel attention mechanism to better model stock relationships and intra-stock features.

Findings

EP-GAT outperforms five baseline models across multiple stock datasets.

The energy-based graph effectively captures evolving inter-stock dependencies.

The parallel attention preserves hierarchical intra-stock dynamics.

Abstract

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. The raw dataset and code are available at https://github.com/theflash987/EP-GAT.