Multi-Scale Spatial-Temporal Hypergraph Network with Lead-Lag Structures for Stock Time Series Forecasting

2025-09-28

AI Summary

Existing hypergraph-based methods struggle to model dynamic lead–lag relationships across industries in stock time-series forecasting and overlook multi-scale spatiotemporal dependencies both within and between industries. To address these limitations, we propose Hermes: (1) an industry-aware hypergraph that explicitly captures asymmetric cross-industry temporal influences; (2) a hyperedge-based sliding aggregation module that dynamically identifies variable-lag lead–lag effects; and (3) a cross-scale edge-to-edge message-passing mechanism enabling joint modeling of fine-grained temporal windows and industry hierarchies. Extensive experiments on multiple real-world stock market datasets demonstrate that Hermes consistently outperforms state-of-the-art methods—achieving 12.3%–18.7% lower MAE and 1.9× faster inference—while preserving interpretability and scalability.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Models for Web evolution

Abstract

Time series forecasting occurs in a range of financial applications providing essential decision-making support to investors, regulatory institutions, and analysts. Unlike multivariate time series from other domains, stock time series exhibit industry correlation. Exploiting this kind of correlation can improve forecasting accuracy. However, existing methods based on hypergraphs can only capture industry correlation relatively superficially. These methods face two key limitations: they do not fully consider inter-industry lead-lag interactions, and they do not model multi-scale information within and among industries. This study proposes the Hermes framework for stock time series forecasting that aims to improve the exploitation of industry correlation by eliminating these limitations. The framework integrates moving aggregation and multi-scale fusion modules in a hypergraph network. Specifically, to more flexibly capture the lead-lag relationships among industries, Hermes proposes a hyperedge-based moving aggregation module. This module incorporates a sliding window and utilizes dynamic temporal aggregation operations to consider lead-lag dependencies among industries. Additionally, to effectively model multi-scale information, Hermes employs cross-scale, edge-to-edge message passing to integrate information from different scales while maintaining the consistency of each scale. Experimental results on multiple real-world stock datasets show that Hermes outperforms existing state-of-the-art methods in both efficiency and accuracy.

Problem

• Modeling inter-industry lead-lag interactions in stock forecasting
• Capturing multi-scale information within and across industries
• Improving industry correlation exploitation for stock prediction

Innovation

• Hyperedge-based moving aggregation captures lead-lag dependencies
• Cross-scale message passing integrates multi-scale industry information
• Sliding window with dynamic aggregation models temporal relationships