NGAT: A Node-level Graph Attention Network for Long-term Stock Prediction

TL;DR

This paper introduces NGAT, a novel node-level graph attention network designed for long-term stock prediction, addressing limitations of existing models in complexity, generalization, and graph structure comparison.

Contribution

We propose a specialized long-term stock prediction task and develop NGAT, a graph attention network that improves model effectiveness and offers a new way to compare corporate relationship graphs.

Findings

NGAT outperforms existing models on two datasets.

Experimental results validate the effectiveness of the proposed approach.

The study highlights limitations of current graph comparison methods.

Abstract

Graph representation learning methods have been widely adopted in financial applications to enhance company representations by leveraging inter-firm relationships. However, current approaches face three key challenges: (1) The advantages of relational information are obscured by limitations in downstream task designs; (2) Existing graph models specifically designed for stock prediction often suffer from excessive complexity and poor generalization; (3) Experience-based construction of corporate relationship graphs lacks effective comparison of different graph structures. To address these limitations, we propose a long-term stock prediction task and develop a Node-level Graph Attention Network (NGAT) specifically tailored for corporate relationship graphs. Furthermore, we experimentally demonstrate the limitations of existing graph comparison methods based on model downstream task performance. Experimental results across two datasets consistently demonstrate the effectiveness of our proposed task and model. The project is publicly available on GitHub to encourage reproducibility and future research.