Enhancing implied volatility forecasting: multi-model approaches for the S\&P500 index

Document Type : Research Article

Authors

Department of Mathematics, Allameh Tabataba’i University

Abstract

Implied volatility is a crucial indicator in financial markets‎, ‎as it reflects market expectations of future volatility and serves as a cornerstone for option pricing‎, ‎risk management‎, ‎and asset allocation‎. ‎Accurate tracking and forecasting of implied volatility are essential for investors and portfolio managers to optimize returns and manage risks effectively‎. ‎
‎‎‎‎This paper explores several modeling‎‎ approaches for forecasting the implied volatility of the S\&P 500 index‎, ‎focusing on exponential autoregressive conditional heteroskedasticity (EGARCH)‎, ‎long short-term memory (LSTM) neural networks‎, ‎and a non-linear autoregressive model with exogenous inputs (NARX)‎. ‎In addition‎, ‎a rough fractional stochastic volatility (RFSV) model is also examined‎. ‎The empirical study demonstrates that the LSTM model offers superior forecasting performance compared to EGARCH‎, ‎NARX‎, ‎and RFSV‎. ‎These findings have important implications for practitioners and researchers aiming to enhance risk management and trading strategies.

Keywords

Main Subjects

References

[1] M. Bennedsen, A. Lunde, M.S. Pakkanen, Decoupling the short-and long-term behavior of stochastic volatility, J. Financ. Econ. 20 (2022) 961–1006.
[2] T. Bollerslev, Generalized autoregressive conditional heteroskedasticity, J. Econom. 31 (1986) 307–327.
[3] B.J. Christensen, N.R. Prabhala, The relation between implied and realized volatility, J. Financ. Econ. 50 (1998) 125–150.
[4] E. Daal, A. Naka, J.S. Yu, Volatility clustering, leverage effects, and jump dynamics in the US and emerging Asian equity markets, J. Bank. Finance 31 (2007) 2751–2769.
[5] R. D’Ecclesia, D.M. Clementi, Volatility in the stock market: ANN versus parametric models, Ann. Oper. Res. 299 (2021) 1101–1127.
[6] A. Deng, B. Hooi, Graph neural network-based anomaly detection in multivariate time series, Proceedings of the AAAI Conference on Artificial Intelligence 35 (2021) 4027–4035.
[7] R.G. Donaldson, M. Kamstra, An artificial neural network—GARCH nodel for international stock return volatility, J. Empir. Finance. 4 (1997) 17–46.
[8] O.E. Euch, M. Rosenbaum, The characteristic function of rough Heston models, Math. Financ. 29 (2019) 3–38.
[9] S. Fallah, F. Mehrdoust, A study of American options under stochastic volatility and double exponential jumps, J. Math. Model. 13(2) (2025) 467–484.
[10] J. Gatheral, T. Jaisson, M. Rosenbaum, Volatility is rough, Quant. Finance 18 (2018) 933–949.
[11] A. Goyal, A. Saretto, Cross-section of option returns and volatility, J. Financ. Econ. 94 (2009) 310–326.
[12] D.D. Hawley, J.D. Johnson, D. Raina, Artificial neural systems: A new tool for financial decision making, Financ. Anal. J. 46 (1990) 63–72.
[13] S.L. Heston, A closed-form solution for options with stochastic volatility, Rev. Financ. Stud. 6 (1993) 327–343.
[14] S. Hochreiter, J. Schmidhuber, Long short-term memory, Neural Comput. 9 (1997) 1735–1780.
[15] X. Huang, H. Cao, B. Jia, Optimization of Levenberg Marquardt algorithm applied to nonlinear systems, Processes 11 (2023) 1794.
[16] M. Kazemi, H.M. Peyhani, M. Akbari, A novel leading moving average indicator using ANFIS-Wavelet hybrid method for financial market forecasting, J. Math. Model. 13(4) (2025) 775–788.
[17] H.Y. Kim, C.H. Won, Forecasting the volatility of stock price index: A hybrid model integrating LSTM with multiple GARCH-type models, Expert Syst. Appl. 103 (2018) 25–37.
[18] F.G. Miranda, N. Burgess, Modelling market volatilities: the neural network perspective, Eur. J. Financ. 3 (1997) 137–157.
[19] D.B. Nelson, Conditional heteroskedasticity in asset returns: a new approach, Econometrica 59 (1991) 347–370.
[20] S.H. Poon, C.W.J. Granger, Forecasting volatility in financial markets: A review, J. Econ. Lit. 41 (2003) 478–539.
[21] A. Stokes, A.S. Abou-Zaid, Forecasting foreign exchange rates using artificial neural networks: a trader’s approach, Int. J. Monet. Econ. Finance 5 (2012) 370–394.
[22] P. Thakkar, K. Chaudhari, A comprehensive survey on deep neural networks for stock market: The need, challenges, and future directions, Expert Syst. Appl. 177 (2021) 114800.
[23] R.S. Tsay, Analysis of Financial Time Series, John Wiley & SONS, 2005.
[24] P. Zhao, H. Zhu, W.S.H. NG, D.L. Lee, From GARCH to neural network for volatility forecast, Proceedings of the AAAI Conference on Artificial Intelligence 35 (2024) 16998–17006.
Journal of Mathematical Modeling
Volume 14, Issue 1
March 2026
Pages 75-91

Files

Share

How to cite

Statistics