Copyright © 2025 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{184954,
        author = {Aishwarya Narale and Dr Pranita Jain and prof sumeet dhillon},
        title = {Data Mining-Based Forecasting of Financial Time Series using Deep Learning Architectures},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {4},
        pages = {3818-3822},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=184954},
        abstract = {Since stock market forecasting has ramifications for traders, investors, and policymakers, it has attracted a lot of attention.  Machine learning and deep learning techniques are being adopted because traditional statistical models frequently fall short in capturing the nonlinear and very volatile character of stock markets.  The performance of three deep learning architectures—Multilayer Perceptron (MLP), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU)—as well as an ensemble technique in predicting the stock prices of Apple Inc. (AAPL) is examined in this study.  Sequences for supervised learning were created by processing historical daily stock data. Several error measures, such as average absolute error (MAE), Root Mean Square Error (RMSE), Coefficient of Determination (R2), mean absolute percentage error (MAPE), and Symmetric Means Absolute Percentage Error (SMAPE), were used to assess the models.  In terms of capturing temporal dependencies, the results show that recurrent architecture (like LSTM or GRU) perform better than conventional MLP. Furthermore, the Ensemble model delivers the lowest prediction error and the highest reliability, demonstrating the advantages of combining multiple architectures. These findings provide insights into selecting robust predictive models for financial time-series forecasting.},
        keywords = {Stock Forecasting, Deep Learning, LSTM, GRU, MLP, Ensemble Learning, Financial Prediction},
        month = {September},
        }