Extracting Structured Insights from Financial News: An Augmented LLM Driven Approach

TL;DR

This paper introduces a novel LLM-based system for extracting structured, company-specific insights from unstructured financial news, including tickers and sentiment, validated on a large dataset and made accessible via a real-time API.

Contribution

The paper presents the first scalable system using LLMs for granular, per-company sentiment analysis from financial news, with a validation framework and public dataset.

Findings

90% of articles accurately include relevant tickers

22% of articles reveal additional relevant tickers

System operates in real-time via an API

Abstract

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.