Modeling and Detecting Company Risks from News: A Case Study in Bloomberg News

TL;DR

This paper develops a computational framework to automatically extract company risk factors from news articles, demonstrating its effectiveness on a large dataset and highlighting the limitations of current large language models in this task.

Contribution

The study introduces a new schema for classifying company risk factors and benchmarks various machine learning models, including fine-tuned language models, for risk detection from news.

Findings

Fine-tuned models outperform zero-shot LLMs in risk detection.

Large language models like LLaMA-2 have limited effectiveness in this task.

Analyzing 277K news articles provides valuable insights into company and industry risks.

Abstract

Identifying risks associated with a company is important to investors and the well-being of the overall financial market. In this study, we build a computational framework to automatically extract company risk factors from news articles. Our newly proposed schema comprises seven distinct aspects, such as supply chain, regulations, and competitions. We sample and annotate 744 news articles and benchmark various machine learning models. While large language models have achieved huge progress in various types of NLP tasks, our experiment shows that zero-shot and few-shot prompting state-of-the-art LLMs (e.g. LLaMA-2) can only achieve moderate to low performances in identifying risk factors. And fine-tuned pre-trained language models are performing better on most of the risk factors. Using this model, we analyze over 277K Bloomberg news articles and demonstrate that identifying risk factors from news could provide extensive insight into the operations of companies and industries.