Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.18775 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914172218900480 |
|---|---|
| author | Chiu, Wei-Ning Wang, Yu-Hsiang Hsiao, Andy Huang, Yu-Shiang Wang, Chuan-Ju |
| author_facet | Chiu, Wei-Ning Wang, Yu-Hsiang Hsiao, Andy Huang, Yu-Shiang Wang, Chuan-Ju |
| contents | A multitude of interconnected risk events -- ranging from regulatory changes to geopolitical tensions -- can trigger ripple effects across firms. Identifying inter-firm risk relations is thus crucial for applications like portfolio management and investment strategy. Traditionally, such assessments rely on expert judgment and manual analysis, which are, however, subjective, labor-intensive, and difficult to scale. To address this, we propose a systematic method for extracting inter-firm risk relations using Form 10-K filings -- authoritative, standardized financial documents -- as our data source. Leveraging recent advances in natural language processing, our approach captures implicit and abstract risk connections through unsupervised fine-tuning based on chronological and lexical patterns in the filings. This enables the development of a domain-specific financial encoder with a deeper contextual understanding and introduces a quantitative risk relation score for transparency, interpretable analysis. Extensive experiments demonstrate that our method outperforms strong baselines across multiple evaluation settings. Our codes are available at https://github.com/cnclabs/codes.fin.relation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_18775 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Financial Risk Relation Identification through Dual-view Adaptation Chiu, Wei-Ning Wang, Yu-Hsiang Hsiao, Andy Huang, Yu-Shiang Wang, Chuan-Ju Computation and Language Artificial Intelligence A multitude of interconnected risk events -- ranging from regulatory changes to geopolitical tensions -- can trigger ripple effects across firms. Identifying inter-firm risk relations is thus crucial for applications like portfolio management and investment strategy. Traditionally, such assessments rely on expert judgment and manual analysis, which are, however, subjective, labor-intensive, and difficult to scale. To address this, we propose a systematic method for extracting inter-firm risk relations using Form 10-K filings -- authoritative, standardized financial documents -- as our data source. Leveraging recent advances in natural language processing, our approach captures implicit and abstract risk connections through unsupervised fine-tuning based on chronological and lexical patterns in the filings. This enables the development of a domain-specific financial encoder with a deeper contextual understanding and introduces a quantitative risk relation score for transparency, interpretable analysis. Extensive experiments demonstrate that our method outperforms strong baselines across multiple evaluation settings. Our codes are available at https://github.com/cnclabs/codes.fin.relation. |
| title | Financial Risk Relation Identification through Dual-view Adaptation |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2509.18775 |