Bridging the Gap Between Natural Language and Market Dynamics via High-Dimensional Representation Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913172010565632 |
|---|---|
| author | Jeong, Yujin Jung, Noelle Leung, Brian Y. C. |
| author_facet | Jeong, Yujin Jung, Noelle Leung, Brian Y. C. |
| contents | Traditional multi-modal financial forecasting often relies on scalar sentiment scores, which fail to capture the nuances of financial news. To address this information loss, this paper explores high-dimensional representation learning by replacing discrete polarity ratings with dense FinBERT embeddings within a Transformer-based forecasting architecture. We benchmarked various embedding strategies on the FNSPID dataset, including raw embeddings, attention-weighted aggregation, and a custom Siamese network. While the attention-based mechanism struggled with the low signal-to-noise ratio typical of financial data, the integration of Siamese-optimized embeddings outperformed both the scalar baseline and raw embedding approaches, demonstrating that preserving high-dimensional narrative context yields improved predictive accuracy for short-term stock price movements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_30652 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Bridging the Gap Between Natural Language and Market Dynamics via High-Dimensional Representation Learning Jeong, Yujin Jung, Noelle Leung, Brian Y. C. Machine Learning Traditional multi-modal financial forecasting often relies on scalar sentiment scores, which fail to capture the nuances of financial news. To address this information loss, this paper explores high-dimensional representation learning by replacing discrete polarity ratings with dense FinBERT embeddings within a Transformer-based forecasting architecture. We benchmarked various embedding strategies on the FNSPID dataset, including raw embeddings, attention-weighted aggregation, and a custom Siamese network. While the attention-based mechanism struggled with the low signal-to-noise ratio typical of financial data, the integration of Siamese-optimized embeddings outperformed both the scalar baseline and raw embedding approaches, demonstrating that preserving high-dimensional narrative context yields improved predictive accuracy for short-term stock price movements. |
| title | Bridging the Gap Between Natural Language and Market Dynamics via High-Dimensional Representation Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2605.30652 |