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{178444,
        author = {S.Vidhi Iyer and Prince Sengar},
        title = {Hybrid Machine Learning Model Based Prediction Analysis of Stocks},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {4454-4456},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=178444},
        abstract = {The prediction of stock market behavior, including stock prices and exchange rates, has remained a prominent area of research among analysts and academics. The volatile nature of stock movements is strongly influenced by financial news, which plays a pivotal role in market trends. Despite this, prior research has often relied on superficial textual features, neglecting deeper semantic relationships. This study proposes a hybrid machine learning framework that integrates both structured stock data and unstructured financial news to improve the accuracy of stock trend forecasting. The model combines Long Short-Term Memory (LSTM) networks with Extreme Gradient Boosting (XGBoost), leveraging the sequential modeling capabilities of LSTM alongside the powerful ensemble learning of XGBoost. This hybrid strategy outperforms traditional statistical approaches and single-model baselines. Experimental results highlight the strength of machine learning techniques—particularly the LSTM–XGBoost combination—in capturing complex dependencies for more accurate financial predictions.},
        keywords = {XGBoost, Machine Learning (ML), Root Mean Squared Error (RMSE), Long Short Term Memory (LSTM)},
        month = {May},
        }