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{207177,
        author = {Krishnaraj P and S. Rita and Jitendra Jaiswal and Dinesh G},
        title = {Stock Price Prediction Using Long Short-Term Memory (LSTM): A Deep Learning Approach for Financial Time Series Forecasting},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {2},
        pages = {4110-4117},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=207177},
        abstract = {Stock market prediction is one of the most challenging problems in financial analytics because prices are influenced by multiple dynamic factors, including economic conditions, investor sentiment, company performance, and global events. Traditional statistical forecasting techniques often fail to capture the nonlinear and sequential characteristics of financial time-series data. Long Short-Term Memory (LSTM) networks have emerged as an effective deep learning approach for modelling temporal dependencies in such data. This study presents a deep learning framework for forecasting stock closing prices using an LSTM neural network. Historical stock market data are collected from publicly available financial sources and preprocessed through data cleaning, Min-Max normalization, and sequence generation, before being split into training and testing sets. Model performance is evaluated using Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Square Error (RMSE), with predicted prices also compared visually against actual market prices. The proposed approach demonstrates that LSTM networks can effectively capture long-term dependencies in financial time-series data and produce reliable short-term forecasts under normal market conditions. While unpredictable economic events and volatility remain significant challenges, the findings indicate that deep learning offers a promising alternative to conventional forecasting methods, providing a simple and reproducible foundation for future research involving hybrid models and technical indicators.},
        keywords = {Artificial Intelligence, Deep Learning, Financial Time Series, Forecasting, Long Short-Term Memory, Python, Stock Market Prediction},
        month = {July},
        }