Optimization and Validation of an Intelligent Machine Learning Framework for Robust Financial Market Time Series Forecasting

The paper introduced an optimized and tested smart ML approach for robust financial market TSF. The proposed framework incorporates a comprehensive data preprocessing, feature engineering, BHO, and thorough validation process to improve the forecasting accuracy and generalizability across various financial markets. Through comparative experiments, the proposed model outperformed ARIMA, LSTM, GRU, Transformer models in all performance metrics including accuracy, precision, recall, F1-score, AUC, RMSE, MAE, MAPE and R². The reliability and stability of the proposed approach were also verified by other tests, such as cross validation, cross market evaluation and robustness analysis under noisy conditions. In addition, the performance in terms of training and prediction times emphasizes its computational efficiency for practical use. The proposed framework could be a valuable tool for intelligent financial analytics, algorithmic trading, and investment decision support. For future work, we plan to introduce real-time streaming financial information and explainable artificial intelligence methods and reinforcement learning to better enhance the adaptiveness of the forecasting performance in markets with high dynamic characteristic.

1.    Hamid Alghamdi, Saad Alqithami, A robust machine learning framework for stock market classification, Expert Systems with Applications, Volume 294, 2025, 128573, ISSN 0957-4174, https://doi.org/10.1016/j.eswa.2025.128573. 2.    Haque, M.S., Ahmed, M.S., Rahman, M.T. et al. An interpretable machine learning framework for predicting next day firm level market stress in the Dhaka Stock Exchange. Discov Artif Intell 6, 1066 (2026). https://doi.org/10.1007/s44163-026-02065-7 3.    Shakri, I. H. (2021). Time series prediction using machine learning: A case of Bitcoin returns. Studies in Economics and Finance, 39(3), 458–470. 4.    Azizi, S. (2026). Leveraging Machine Learning for Financial Forecasting: Distinguishing Market Trends from Oscillations in ETFs. Journal of Risk and Financial Management, 19(4), 262. https://doi.org/10.3390/jrfm19040262 5.    Khan W, Ghazanfar MA, Azam MA, et al. Stock market prediction using machine learning classifiers and social media, news. Journal of Ambient Intelligence and Humanized Computing 2022; 13: 3433–3456. doi: 10.1007/s12652-020-01839-w 6.    Gurrib, I., & Kamalov, F. (2022). Predicting bitcoin price movements using sentiment analysis: A machine learning approach. Studies in Economics and Finance, 39(3), 347–364. 7.    Lan Ouyang. 2025. Research on Financial Time Series Forecasting Model Based on Machine Learning. In Proceedings of the 2025 International Conference on Economic Management and Big Data Application (ICEMBDA '25). Association for Computing Machinery, New York, NY, USA, 349–353. https://doi.org/10.1145/3770177.3770233 8.    Prasad A, Seetharaman A. Importance of machine learning in making investment decision in stock market. Vikalpa: The Journal for Decision Makers 2021; 46(4): 209–222. doi: 10.1177/02560909211059992 9.    Deniz NoorMohammadzadehMaleki, Sina Abbaskhani, Amirfarhad Farhadi, Azadeh Zamanifar, Artificial intelligence methods for financial market prediction: A systematic review, Computers and Electrical Engineering, Volume 134, 2026, 111110, https://doi.org/10.1016/j.compeleceng.2026.111110. 10. Dezhkam, A., Manzuri, M. T., Aghapour, A., Karimi, A., Rabiee, A., & Shalmani, S. M. (2023). A Bayesian-based classification framework for financial time series trend prediction. The Journal of supercomputing, 79(4), 4622–4659. https://doi.org/10.1007/s11227-022-04834-4