Extracting Structured Insights from Financial News: An Augmented LLM Driven Approach
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929430731948032 |
|---|---|
| author | Dolphin, Rian Dursun, Joe Chow, Jonathan Blankenship, Jarrett Adams, Katie Pike, Quinton |
| author_facet | Dolphin, Rian Dursun, Joe Chow, Jonathan Blankenship, Jarrett Adams, Katie Pike, Quinton |
| contents | Financial news plays a crucial role in decision-making processes across the financial sector, yet the efficient processing of this information into a structured format remains challenging. This paper presents a novel approach to financial news processing that leverages Large Language Models (LLMs) to overcome limitations that previously prevented the extraction of structured data from unstructured financial news. We introduce a system that extracts relevant company tickers from raw news article content, performs sentiment analysis at the company level, and generates summaries, all without relying on pre-structured data feeds. Our methodology combines the generative capabilities of LLMs, and recent prompting techniques, with a robust validation framework that uses a tailored string similarity approach. Evaluation on a dataset of 5530 financial news articles demonstrates the effectiveness of our approach, with 90% of articles not missing any tickers compared with current data providers, and 22% of articles having additional relevant tickers. In addition to this paper, the methodology has been implemented at scale with the resulting processed data made available through a live API endpoint, which is updated in real-time with the latest news. To the best of our knowledge, we are the first data provider to offer granular, per-company sentiment analysis from news articles, enhancing the depth of information available to market participants. We also release the evaluation dataset of 5530 processed articles as a static file, which we hope will facilitate further research leveraging financial news. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_15788 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Extracting Structured Insights from Financial News: An Augmented LLM Driven Approach Dolphin, Rian Dursun, Joe Chow, Jonathan Blankenship, Jarrett Adams, Katie Pike, Quinton Computation and Language I.2.7 Financial news plays a crucial role in decision-making processes across the financial sector, yet the efficient processing of this information into a structured format remains challenging. This paper presents a novel approach to financial news processing that leverages Large Language Models (LLMs) to overcome limitations that previously prevented the extraction of structured data from unstructured financial news. We introduce a system that extracts relevant company tickers from raw news article content, performs sentiment analysis at the company level, and generates summaries, all without relying on pre-structured data feeds. Our methodology combines the generative capabilities of LLMs, and recent prompting techniques, with a robust validation framework that uses a tailored string similarity approach. Evaluation on a dataset of 5530 financial news articles demonstrates the effectiveness of our approach, with 90% of articles not missing any tickers compared with current data providers, and 22% of articles having additional relevant tickers. In addition to this paper, the methodology has been implemented at scale with the resulting processed data made available through a live API endpoint, which is updated in real-time with the latest news. To the best of our knowledge, we are the first data provider to offer granular, per-company sentiment analysis from news articles, enhancing the depth of information available to market participants. We also release the evaluation dataset of 5530 processed articles as a static file, which we hope will facilitate further research leveraging financial news. |
| title | Extracting Structured Insights from Financial News: An Augmented LLM Driven Approach |
| topic | Computation and Language I.2.7 |
| url | https://arxiv.org/abs/2407.15788 |