---
title: "Dynamic Higher-Order Relations and Event-Driven Temporal Modeling for Stock Price Forecasting"
authors:
  - "Kijeong Park"
  - "Sungchul Hong"
  - "Jong-June Jeon"
doi: "10.24963/ijcai.2025/673"
url: "https://ijcai.org/proceedings/2025/673"
pdf: "https://ijcai.org/proceedings/2025/0673.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "6048-6056"
track: "Main Track"
keywords:
  - "Machine Learning: ML: Deep learning architectures"
  - "Multidisciplinary Topics and Applications: MTA: Finance"
  - "Machine Learning: ML: Supervised Learning"
  - "Machine Learning: ML: Applications"
---

# Dynamic Higher-Order Relations and Event-Driven Temporal Modeling for Stock Price Forecasting

Kijeong Park, Sungchul Hong, Jong-June Jeon

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 6048-6056. DOI: [10.24963/ijcai.2025/673](https://doi.org/10.24963/ijcai.2025/673)

## Abstract

In stock price forecasting, modeling the probabilistic dependence between stock prices within a time-series framework has remained a persistent and highly challenging area of research. We propose a novel model to explain the extreme co-movement in multivariate data with time-series dependencies. Our model incorporates a Hawkes process layer to capture abrupt co-movements, thereby enhancing the temporal representation of market dynamics. We introduce dynamic hypergraphs into our model adapting to higher-order (groupwise rather than pairwise) relationships within the stock market. Extensive experiments on real-world benchmarks demonstrate the robustness of our approach in predictive performance and portfolio stability.