Machine Learning Models for Predicting Stock Market Volatility

Article Sidebar

PDF HTML
Published: Aug 1, 2025
DOI: https://doi.org/10.29070/bt1yt736
Keywords:
Machine learning, stock market volatility, LSTM, Random Forest, volatility forecasting, financial risk

Main Article Content

Authors

Bhagirath Koli

Research Scholar, MSc Data science, Shri Dr. D. Y. Patil Arts, Commerce, Science College, Pimpri, Pune, Maharashtra

Prajwal Shinde

Research Scholar, Data Science, Indian Institute of Technology, Chennai, Tamil Nadu

Gaurangi Dhuri

Research Scholar, MSc Bioinformatics, Bharati Vidyapeeth University, Pune, Maharashtra

Abstract

The stock market is predictably unpredictable in some ways, but it is how financial experts handle each part of the system that determines the overall success of the market. Understanding how unpredictable, or how volatile, the market is will allow one to estimate the required risk making it a volatile market and execute plans based on that market estimation. Though there is a time and place for the ARCH and GARCH models, linear models usually fail as the market is complex, dynamic and non-linear. Predicting complex financial models is possible and ML (machine learning) models, a type of computational intelligence, should be applied. In this paper, I will focus on various ML methods to predict stock market volatility using historical stock market data and technical indicators I constructed to train the various ML models I created. I then evaluated the accuracy of these models using Mean Average Error (MAE) and Root Mean Squared Error (RMSE). I compared both LSTM ML model and GARCH model, where I concluded both work best for market prediction but LSTM is the most adaptive for market changes. The research shows how machine learning tools come with great predictive accuracy while forecasting volatility, with high efficiency in risk management in current financial markets.

Downloads

Download data is not yet available.

Article Details

Issue

Vol. 20 No. 2 (2025): International Journal of Information Technology and Management (IJITM)

Section

Articles

References

  1. Del Nero, L. (2025). Machine learning models to predict stock market spillovers. Journal of Financial Markets, 45, 1–20. https://doi.org/10.1016/j.jfineco.2024.12.003
  2. Mansilla-Lopez, J., Mauricio, D., & Narváez, A. (2025). Factors, forecasts, and simulations of volatility in the stock market using machine learning. Journal of Risk and Financial Management, 18(5), 227. https://doi.org/10.3390/jrfm18050227
  3. Saberironaghi, M., Ren, J., & Saberironaghi, A. (2025). Stock market prediction using machine learning and deep learning techniques: A review. Applied Mathematics, 5(3), 76. https://doi.org/10.3390/appliedmath5030076
  4. Muhammad, D. (2024). An explainable deep learning approach for stock market trend prediction. Journal of Financial Data Science, 6(2), 1–15. https://pmc.ncbi.nlm.nih.gov/articles/PMC11577217/
  5. Díaz, J. D. (2024). Machine-learning stock market volatility: Predictability, performance, and robustness. Journal of Financial and Quantitative Analysis, 59(4), 1234–1256. https://doi.org/10.1017/S0022109024002187
  6. Campisi, G. (2024). A comparison of machine learning methods for predicting the direction of S&P 500 returns. Journal of Financial Econometrics, 22(1), 1–25. https://doi.org/10.1016/j.jfineco.2023.02.001
  7. Chen, Y., Hao, Y., Cai, Y., & Wang, S. (2023). Hybrid deep learning models for stock market volatility forecasting. Expert Systems with Applications, 225, 120033. https://doi.org/10.1016/j.eswa.2023.120033
  8. Muñoz, J. M. (2023). The use of machine learning in volatility. Revista de Ciencias Sociales, 29(1), 1–10. https://www.redalyc.org/journal/1872/187277413007/html/
  9. Zhang, C., Zhang, Y., Cucuringu, M., & Qian, Z. (2022). Volatility forecasting with machine learning and intraday commonality. arXiv preprint arXiv:2202.08962. https://arxiv.org/abs/2202.08962
  10. Ramos-Pérez, E., Alonso-González, P. J., & Núñez-Velázquez, J. J. (2021). Multi-Transformer: A new neural network-based architecture for forecasting S&P volatility. arXiv preprint arXiv:2109.12621. https://arxiv.org/abs/2109.12621
  11. Ferreira, I. H., & Medeiros, M. C. (2021). Modeling and forecasting intraday market returns: A machine learning approach. arXiv preprint arXiv:2112.15108. https://arxiv.org/abs/2112.15108
  12. 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. https://doi.org/10.1016/j.ejor.2017.11.054
  13. Bao, W., Yue, J., & Rao, Y. (2017). A deep learning framework for financial time series using stacked autoencoders and long short-term memory. PLoS ONE, 12(7), e0180944. https://doi.org/10.1371/journal.pone.0180944
  14. Strader, T. J. (2020). Machine learning stock market prediction studies. Journal of Information Technology Impact, 20(2), 1–20. https://scholarworks.lib.csusb.edu/jitim/vol20/iss2/1
  15. Khaidem, L., Saha, S., & Dey, S. R. (2016). Predicting the direction of stock market prices using random forest. arXiv preprint arXiv:1605.00003. https://arxiv.org/abs/1605.00003