Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{207175,
        author = {Priyanka Mohan and Vinay B V and Sandeshgowda B M},
        title = {Augmenting Financial Decision Systems through Natural Language Processing: A Review of Analytical Models, Real- World Applications, and Emerging Research Trends},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {2},
        pages = {4497-4506},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=207175},
        abstract = {The increasing volume of data generated in the financial sector makes NLP increasingly significant. Although the data available in the form of financial news, filings, earnings calls, social media content is useful for extracting signals concerning the current state of the market, the huge volumes of data along with complex language hinder its manual processing. This paper discusses various methods used in the financial NLP field, including rule-based lexicons, statistical machine learning approaches, deep learning models, transformer architecture (such as BERT, FinBERT, BloombergGPT, FinGPT) as well as the recent developments like RAG and financial agents that are based on LLMs. The review contains the introduction to the main areas of applications of financial NLP such as sentiment analysis, information extraction, algorithmic trading, detection of frauds and credit risks, RegTech, and question answering. The survey also considers language characteristics, data availability, temporal drift, interpretability, and computational needs as the major challenges of financial NLP. The accompanying implementation has been greatly Improved in this revision: Rather than an example with a small set of documents, the full NLP pipeline for classics (scoring of word lists, TF-IDF features, machine learning classification, and LDA topic modeling) was performed on the 2,000-document financial sentiment analysis corpus, and all numbers, confusion matrices, ROC curves, and topic distributions were derived from this analysis rather than a made-up one. References were added to emphasize fifteen papers from 2023 through 2025, indicating the trend toward using LLMs in financial NLP.},
        keywords = {Natural Language Processing; Financial Text Mining; Sentiment Analysis; BERT; FinBERT; Large Language Models; BloombergGPT; FinGPT; Retrieval-Augmented Generation; Deep Learning; Algorithmic Trading; Information Extraction.},
        month = {July},
        }