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{188838,
        author = {Guruprasad Patil and Amit and Amogh Hugar and Prof. Ashwini Hatti},
        title = {FinFormer: A Multi-Modal Stock Price Prediction Framework integrating Transformer Networks and Sentiment Analysis},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {3809-3815},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=188838},
        abstract = {The financial market is a complex, non-linear system influenced by numerous factors, including historical trends, economic news, and investor sentiment. Traditional forecasting models like ARIMA and basic Recurrent Neural Networks (RNNs) such as LSTM primarily rely on quantitative historical data. While effective for short-term dependencies, these univariate models often fail to capture the qualitative impact of real-world news, leading to suboptimal predictions during volatile periods. This paper proposes "FinFormer," a novel Multi-Modal Deep Learning framework integrating a Transformer-based neural network with Natural Language Processing (NLP). The system uses a Self-Attention mechanism to capture long-term dependencies in stock data and fuses this with real-time news sentiment scores derived using VADER. Experimental results on National Stock Exchange (NSE) data show that FinFormer achieves a lower Mean Squared Error (MSE) compared to baseline LSTM architectures and effectively identifies trend reversals driven by external sentiment.},
        keywords = {Stock Market Prediction, Deep Learning, Transformer, Natural Language Processing (NLP), Sentiment Analysis, Multi-Modal Learning.},
        month = {December},
        }