Improving Stock Price Volatility Prediction Models Using Machine Learning and Statistical Techniques
DOI:
https://doi.org/10.48165/gjs.2025.2209Keywords:
Stock price volatility, Machine learning, Grid search, Financial prediction, Random forest, Linear regressionAbstract
This research aims to improve forecasting models for the volatility of stock prices in Saudi banks by using machine learning algorithms and parameter optimization techniques such as Grid Search. The goal of this study is to improve forecasting models. Grid Search is going to be used in order to attain this goal. We examined the price information that Al Rajhi Bank has accumulated over a considerable length of time and the results were analyzed. The starting and closing prices, the highest and lowest values, the trading volume, and the daily percentage change were all included in this. Additionally, the trade volume was an important factor. In order to throw light on the general patterns that were present, we used descriptive data analysis. Given that the Saudi financial market is driven by both internal and external variables, the data indicated that there was a substantial degree of variation in both the trading volume and the price. This is typical for the Saudi market since it is influenced by both types of factors. Next, a machine learning model that was produced based on Random Forest was developed, along with a linear regression model and a ridge model. After that these models were constructed. Taking into account the outcomes of the research, the Random Forest model, which had been enhanced via the use of Grid Search, was the most accurate in terms of predicting future volatility. The coefficient of determination (R2) value of about 0.86 makes it superior than linear models in terms of its capacity to make assumptions and predictions. Moreover, the results indicate the need of using nonlinear models in combination with optimization methodologies in order to focus on the complicated relationships that exist between financial issues and price fluctuations. This is because the outcomes highlight the need to use nonlinear models.
References
[1] O. B. Sezer, M. U. Gudelek, and A. M. Ozbayoglu, “Financial time series forecasting with deep learning: A systematic literature review: 2005–2019,” Applied Soft Computing, vol. 90, p. 106181, 2020.
[2] J. C. Hung, “Robust Kalman filter based on a fuzzy GARCH model to forecast volatility using particle swarm optimization,” Soft Computing, vol. 19, no. 10, pp. 2861–2869, 2015.
[3] P. Shiguihara, A. De Andrade Lopes, and D. Mauricio, “Dynamic Bayesian network modeling, learning, and inference: A survey,” IEEE Access, vol. 9, pp. 117639–117648, 2021.
[4] T. N. Nguyen, M. N. Tran, D. Gunawan, and R. Kohn, “A statistical recurrent stochastic volatility model for stock markets,” Journal of Business & Economic Statistics, vol. 41, no. 2, pp. 414–428, 2023.
[5] S. Lee and P. Cho, “Graph-Based Stock Volatility Forecasting with Effective Transfer Entropy and Hurst-Based Regime Adaptation,” Fractal and Fractional, vol. 9, no. 6, p. 339, 2025.
[6] E. T. Sivadasan, N. M. Sundaram, and R. Santhosh, “Stock market forecasting using deep learning with long short-term memory and gated recurrent unit,” Soft Computing, vol. 28, no. 4, pp. 3267–3282, 2024.
[7] K. Zheng, S. Yu, and B. Chen, “Ci-GNN: A granger causality-inspired graph neural network for interpretable brain network-based psychiatric diagnosis,” Neural Networks, vol. 172, p. 106147, 2024.
[8] M. Summer, “Financial contagion and network analysis,” Annual Review of Financial Economics, vol. 5, no. 1, pp. 277–297, 2013.
[9] P. Cho and K. Kim, “Global collective dynamics of financial market efficiency using attention entropy with hierarchical clustering,” Fractal and Fractional, vol. 6, no. 10, p. 562, 2022.
[10] K. Baltakys, M. Baltakienė, N. Heidari, A. Iosifidis, and J. Kanniainen, “Predicting the trading behavior of socially connected investors: Graph neural network approach with implications to market surveillance,” Expert Systems with Applications, vol. 228, p. 120285, 2023.
[11] Q. Chen and C. Y. Robert, “Multivariate realized volatility forecasting with graph neural network,” in Proceedings of the 3rd ACM International Conference on AI in Finance, Nov. 2022, pp. 156–164.
[12] N. Das, B. Sadhukhan, R. Chatterjee, and S. Chakrabarti, “Integrating sentiment analysis with graph neural networks for enhanced stock prediction: A comprehensive survey,” Decision Analytics Journal, vol. 10, p. 100417, 2024.
[13] F. Scarselli, M. Gori, A. C. Tsoi, M. Hagenbuchner, and G. Monfardini, “The graph neural network model,” IEEE Transactions on Neural Networks, vol. 20, no. 1, pp. 61–80, 2008.
[14] Y. A. Ali, E. M. Awwad, M. Al-Razgan, and A. Maarouf, “Hyperparameter search for machine learning algorithms for optimizing the computational complexity,” Processes, vol. 11, no. 2, p. 349, 2023.
[15] L. Yang and A. Shami, “On hyperparameter optimization of machine learning algorithms: Theory and practice,” Neurocomputing, vol. 415, pp. 295–316, 2020.
[16] Escorcia-Gutierrez, J., Mansour, R. F., Beleño, K., Jiménez-Cabas, J., Pérez, M., Madera, N., & Velasquez, K. (2022). “Automated Deep Learning Empowered Breast Cancer Diagnosis Using Biomedical Mammogram Images.” Computers, Materials & Continua, 71(3), 131–144.
[17] P. Novello, G. Poëtte, D. Lugato, and P. M. Congedo, “Goal-oriented sensitivity analysis of hyperparameters in deep learning,” Journal of Scientific Computing, vol. 94, no. 3, p. 45, 2023.
[18] Yaghoobi, S. (2025). Enhancing Logical Reasoning and Temporal Dynamics in Complex Systems Through Hybrid Logical Neural and Echo State Networks (Doctoral dissertation, University of Nevada, Reno).
[19] H. Fushing, S. C. Chen, and C. R. Hwang, “Discovering stock dynamics through multidimensional volatility phases,” Quantitative Finance, vol. 12, no. 2, pp. 213–230, 2012.
[20] A. M. Elsheikh and A. A. Elhag, “Machine learning-based analysis of multi-region bone fracture detection and classification using biomedical images,” Alexandria Engineering Journal, vol. 128, pp. 186–199, 2025.
[21] H. A. Salman, A. Kalakech, and A. Steiti, “Random forest algorithm overview,” Babylonian Journal of Machine Learning, pp. 69–79, 2024.
[22] D. M. Belete and M. D. Huchaiah, “Grid search in hyperparameter optimization of machine learning models for prediction of HIV/AIDS test results,” International Journal of Computer Applications, vol. 44, no. 9, pp. 875–886, 2022.
[23] H. Sahour, V. Gholami, J. Torkaman, M. Vazifedan, and S. Saeedi, “Random forest and extreme gradient boosting algorithms for streamflow modeling using vessel features and tree rings,” Environmental Earth Sciences, vol. 80, no. 22, p. 747, 2021.
[24] H. Abdulrahim, S. M. Alshibani, O. Ibrahim, and A. A. Elhag, “Prediction OPEC oil price utilizing long short-term memory and multi-layer perceptron models,” Alexandria Engineering Journal, vol. 110, pp. 607–612, 2025.
