Forecasting the dynamics of the stock market remains one of the most challenging tasks in financial analytical mechanics due to its stochasticity, nonlinearity, and dynamic character. In this paper, the author offers a detailed comparative analysis of two groups of machine learning and deep learning models available on two publicly accessible databases of Yahoo Finance and Kaggle. This research serves as an assessment of the forecast accuracy provided by the LR, RF, and LSTM network for stock price prediction. To guarantee proper model training and validation, the proposed methodology includes data pre-processing, feature engineering, time-series transformation, and model optimization techniques. The following standard error metrics - the mean squared error (MSE), root-mean-squared error (RMSE), mean absolute error (MAE), and the coefficient of determination (R²) were used for evaluating model performance. Based on the empirical results, the LSTM network shows a similar level of accuracy in predicting stock prices as the conventional machine learning approach. Nevertheless, LSTM outperforms the latter model when dealing with enriched feature sets. The results are indicative of the significance of the feature of the dataset as well as its temporal dependencies on the performance of the predictive model, indicating that deep learning models outperform in terms of accurately modeling complicated patterns in financial time series data. This research has important implications for building efficient and effective stock market forecasting models.
Fama, E. F. (1970). Efficient capital markets: A review of theory and empirical work. The Journal of Finance, 25(2), 383-417.
Henrique, B. M., Sobreiro, V. A., & Kimura, H. (2019). Machine learning in financial markets: A review. Expert Systems with Applications, 115, 363-377.
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5-32.
Patel, J., Shah, S., Thakkar, P., & Kotecha, K. (2015). Predicting stock market index using fusion of machine learning techniques. Expert Systems with Applications, 42(4), 2162-2172.
Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735-1780.
Sezer, O. B., Gudelek, M. U., & Ozbayoglu, A. M. (2020). Financial time series forecasting with deep learning: A systematic literature review: 2005-2019. Applied Soft Computing, 90, 106181.
Fischer, T., & Krauss, C. (2018). Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research, 270(2), 654-669.
Tin, H. H. K. (2023). Exploring the Potential Impact of Selected Blockchain-Based Financial Applications on the Financial Industry: Opportunities and Challenges. International Journal of Research and Innovation in Applied Science, 8(11), 87-94.
Tin, H. H. K., Aung, T. T., Khaing, M. M., Thu, E. T. T., & Myint, K. L. (2021). Finding the active learning consequences of management information system course: case study of postgraduate and undergraduate students. The Educational Review, USA, 5(3).
Paw, S., Aung, T. T., Khaing, M. M., & Tin, H. H. K. (2025). Analyzing the performance of ChatGPT-4.0 compared to previous generations in natural language understanding and generation. Indian Journal of Science and Research, 5(2), 65-74.
Stock Market Prediction, Machine Learning, Deep Learning, LSTM, Time Series Forecasting, Financial Analytics.
