LLM-Powered News Research Tool for Equity Analysis

Authors

  • Thrivikram Bhat V Department of ISE, BNM Institute of Technology (Affiliated to VTU) Bangalore, Karnataka, India Author
  • Shubham Pathak Department of ISE, BNM Institute of Technology (Affiliated to VTU) Bangalore, Karnataka, India Author
  • Tanvi Bareja Department of ISE, BNM Institute of Technology (Affiliated to VTU) Bangalore, Karnataka, India Author
  • Mamta Sen Department of ISE, BNM Institute of Technology (Affiliated to VTU) Bangalore, Karnataka, India Author
  • Mrs Sindhu N Assistant Professor, Department of ISE, BNM Institute of Technology (Affiliated to VTU) Bangalore, Karnataka, India Author

DOI:

https://doi.org/10.32628/CSEIT25112799

Keywords:

Large Language Models, News Analytics, Equity Research, Sentiment Analysis, Financial Technology, Natural Language Processing

Abstract

As financial markets evolve, extracting timely and actionable insights from news content becomes increasingly critical for equity analysis and investment strategies. The surge in unstructured financial data poses a significant challenge for traditional analysis techniques. This survey investigates how Large Language Models (LLMs) can be harnessed to automate and enhance the interpretation of financial news. We explore a broad range of recent advancements, evaluate system frame- works, identify key obstacles, and discuss promising solutions. Our goal is to illuminate how LLMs are reshaping the landscape of financial analytics and to inspire continued innovation in this space.

Downloads

Download data is not yet available.

References

OpenAI, “GPT-4 Technical Report,” arXiv preprint arXiv:2303.08774, 2023.

A. Manibardo, C. de Benito, S. Gonzalez, and E. Cano, “FinanceGPT: Large Language Models for Financial Text Generation,” arXiv preprint arXiv:2306.02041, 2023.

Srikanth Yerra, “The Role of Azure Data Lake in Scalable and High-Performance Supply Chain Analytics,” International Journal of Scientific Research in Computer Science Engineering and Information Technology, vol. 11, no. 1, pp. 3668–3673, Feb. 2025

J. Lopez-Lira, M. Tang, and K. Wermers, “FinMA: A Benchmark for Financial News Language Models,” arXiv preprint arXiv:2308.11458, 2023.

Yerra, S. (2024). The impact of AI-driven data cleansing on supply chain data accuracy and master data management. Smart Computing Systems, 4(1), 187-191.

P. Yang, H. Sun, and K. Zhang, “FinBERT: A Pretrained Language Model for Financial Communications,” in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020.

D. Araci, “FinBERT: Financial Sentiment Analysis with Pre-trained Language Models,” arXiv preprint arXiv:1908.10063, 2019.

Downloads

Published

08-04-2025

Issue

Vol. 11 No. 2 (2025): March-April

Section

Research Articles

License

Copyright (c) 2025 International Journal of Scientific Research in Computer Science, Engineering and Information Technology

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.