Dynamic Graph Representation with Contrastive Learning for Financial Market Prediction: Integrating Temporal Evolution and Static Relations
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909519384150016 |
|---|---|
| author | Pei, Yunhua Zheng, Jin Cartlidge, John |
| author_facet | Pei, Yunhua Zheng, Jin Cartlidge, John |
| contents | Temporal Graph Learning (TGL) is crucial for capturing the evolving nature of stock markets. Traditional methods often ignore the interplay between dynamic temporal changes and static relational structures between stocks. To address this issue, we propose the Dynamic Graph Representation with Contrastive Learning (DGRCL) framework, which integrates dynamic and static graph relations to improve the accuracy of stock trend prediction. Our framework introduces two key components: the Embedding Enhancement (EE) module and the Contrastive Constrained Training (CCT) module. The EE module focuses on dynamically capturing the temporal evolution of stock data, while the CCT module enforces static constraints based on stock relations, refined within contrastive learning. This dual-relation approach allows for a more comprehensive understanding of stock market dynamics. Our experiments on two major U.S. stock market datasets, NASDAQ and NYSE, demonstrate that DGRCL significantly outperforms state-of-the-art TGL baselines. Ablation studies indicate the importance of both modules. Overall, DGRCL not only enhances prediction ability but also provides a robust framework for integrating temporal and relational data in dynamic graphs. Code and data are available for public access. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_04034 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Dynamic Graph Representation with Contrastive Learning for Financial Market Prediction: Integrating Temporal Evolution and Static Relations Pei, Yunhua Zheng, Jin Cartlidge, John Machine Learning Neural and Evolutionary Computing Computational Finance Temporal Graph Learning (TGL) is crucial for capturing the evolving nature of stock markets. Traditional methods often ignore the interplay between dynamic temporal changes and static relational structures between stocks. To address this issue, we propose the Dynamic Graph Representation with Contrastive Learning (DGRCL) framework, which integrates dynamic and static graph relations to improve the accuracy of stock trend prediction. Our framework introduces two key components: the Embedding Enhancement (EE) module and the Contrastive Constrained Training (CCT) module. The EE module focuses on dynamically capturing the temporal evolution of stock data, while the CCT module enforces static constraints based on stock relations, refined within contrastive learning. This dual-relation approach allows for a more comprehensive understanding of stock market dynamics. Our experiments on two major U.S. stock market datasets, NASDAQ and NYSE, demonstrate that DGRCL significantly outperforms state-of-the-art TGL baselines. Ablation studies indicate the importance of both modules. Overall, DGRCL not only enhances prediction ability but also provides a robust framework for integrating temporal and relational data in dynamic graphs. Code and data are available for public access. |
| title | Dynamic Graph Representation with Contrastive Learning for Financial Market Prediction: Integrating Temporal Evolution and Static Relations |
| topic | Machine Learning Neural and Evolutionary Computing Computational Finance |
| url | https://arxiv.org/abs/2412.04034 |