Financial Time Series Forecasting: A Hybrid Approach Combining AR-GARCH and Machine Learning Models

Shangrong Han

doi:10.62051/pg9aec47

Authors

Shangrong Han

DOI:

https://doi.org/10.62051/pg9aec47

Keywords:

Financial time series forecasting, Machine learning, Hybrid forecasting models, AR-GARCH, LSTM, CNN, Random Forest.

Abstract

Accurately forecasting financial markets remains a central challenge in economics due to the volatile, nonlinear, and complex nature of asset price movements. Traditional statistical models like Autoregressive Generalized Autoregressive Conditional Heteroskedasticity (AR-GARCH) have been widely used for modeling volatility, but often fall short when addressing intricate market patterns. This study systematically compares the predictive capabilities of AR-GARCH, Long Short-Term Memory (LSTM) networks, Convolutional Neural Networks (CNN), Random Forest (RF), and a hybrid ensemble on weekly data from the S&P 500, FTSE 100, and Nikkei 225 indices spanning 2000 to 2024. Performance is evaluated using standard forecasting metrics: Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE). The findings indicate that while each separate model has varying strengths depending on market conditions, the hybrid model consistently achieves superior accuracy by leveraging the diversity of all approaches. These results highlight the benefits of integrating classical econometric approaches with contemporary machine learning techniques to improve forecasting precision and strengthen the robustness of models in financial time series analysis.

Downloads

Download data is not yet available.

References

[1] R.F. Engle, Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation, Econometrica 50 (1982) 987–1007.

[2] T. Bollerslev, Generalized autoregressive conditional heteroskedasticity, J. Econometrics 31 (1986) 307–327.

[3] P.H. Franses, D. Van Dijk, Forecasting stock market volatility using (non-linear) GARCH models, J. Forecast. 15 (1996) 229–235.

[4] S.J. Taylor, Asset Price Dynamics, Volatility, and Prediction, Princeton University Press, Princeton, 2011.

[5] S. Hochreiter, J. Schmidhuber, Long short-term memory, Neural Comput. 9 (1997) 1735–1780.

[6] Y. LeCun, Y. Bengio, G. Hinton, Deep learning, Nature 521 (2015) 436–444.

[7] L. Zhang, C. Aggarwal, G.J. Qi, Stock price prediction via discovering multi-frequency trading patterns, in: Proc. 23rd ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., 2017, pp. 2141–2149.

[8] W. Bao, J. Yue, Y. Rao, A deep learning framework for financial time series using stacked autoencoders and long-short term memory, PLoS One 12 (2017) e0180944.

[9] S. Gu, B. Kelly, D. Xiu, Empirical asset pricing via machine learning, Rev. Financ. Stud. 33 (2020) 2223–2273.

[10] K. He, Q. Yang, L. Ji, J. Pan, Y. Zou, Financial time series forecasting with the deep learning ensemble model, Mathematics 11 (2023) 1054.

[11] J. Janczura, A. Puć, ARX-GARCH probabilistic price forecasts for diversification of trade in electricity markets—variance stabilizing transformation and financial risk-minimizing portfolio allocation, Energies 16 (2023) 807.

[12] M.L. Bianchi, G. De Luca, G. Rivieccio, CoVaR with volatility clustering, heavy tails and non-linear dependence, arXiv preprint arXiv:2009.10764 (2020).

[13] J. Michańków, Ł. Kwiatkowski, J. Morajda, Combining deep learning and GARCH models for financial volatility and risk forecasting, arXiv preprint arXiv:2310.01063 (2023).

[14] J. Wei, S. Yang, Z. Cui, Integrated GARCH-GRU in financial volatility forecasting, arXiv preprint arXiv:2504.09380 (2025).

[15] Z. Zeng, R. Kaur, S. Siddagangappa, S. Rahimi, T. Balch, M. Veloso, Financial time series forecasting using CNN and transformer, arXiv preprint arXiv:2304.04912 (2023).

[16] Z. Wang, L. Wu, Theoretical analysis of the inductive biases in deep convolutional networks, Adv. Neural Inf. Process. Syst. 36 (2023) 74289–74338.

[17] K. Greff, R.K. Srivastava, J. Koutník, B.R. Steunebrink, J. Schmidhuber, LSTM: A search space odyssey, IEEE Trans. Neural Netw. Learn. Syst. 28 (2016) 2222–2232.

[18] O.B. Sezer, M.U. Gudelek, A.M. Ozbayoglu, Financial time series forecasting with deep learning: a systematic literature review: 2005–2019, Appl. Soft Comput. 90 (2020) 106181.

[19] R.P. Masini, M.C. Medeiros, E.F. Mendes, Machine learning advances for time series forecasting, J. Econ. Surv. 37 (2023) 76–111.

[20] M. Zhao, X. Zhang, J. Appiah, M.D. Fontaine, Travel time reliability prediction using random forests, Transp. Res. Rec. 2678 (2024) 531–545.

[21] K. Kakade, I. Jain, A.K. Mishra, Value-at-Risk forecasting: a hybrid ensemble learning GARCH-LSTM based approach, Resour. Policy 78 (2022) 102903.

[22] A. Mahmoud, A. Mohammed, Leveraging hybrid deep learning models for enhanced multivariate time series forecasting, Neural Process. Lett. 56 (2024) 223.

[23] M.H. Ibrahim, A.Z. Baharumshah, M.S. Habibullah, Comparing the performances of GARCH-type models in capturing the stock market volatility in Malaysia, J. Appl. Sci. 14 (2014) 3557–3564.

[24] W.K. Wong, J. Li, Modeling and forecasting trading volume index: GARCH versus TGARCH approach, Q. Rev. Econ. Finance 50 (2010) 319–329.