Return-Based Volatility Proxy Forecasting via a Residual-Correction LSTM–GARCH Hybrid Framework
DOI:
https://doi.org/10.54097/4wx6m038Keywords:
Stock return forecasting, residual correction, GARCH, LSTM.Abstract
Forecasting return-based volatility proxies is challenging in financial markets due to volatility clustering, heavy tails, and nonlinear dynamics. This paper proposes a residual-correction LSTM–GARCH hybrid framework, where GARCH provides a robust econometric backbone, while LSTM learns the nonlinear residual in the log variance-ratio space and performs multiplicative correction. Experiments on a representative ETF show that the proposed RC-LSTM–GARCH achieves better RMSE, MAE, and QLIKE than the GARCH baseline. The proposed design aims to combine the interpretability and stability of GARCH with the nonlinear representation ability of LSTM, thereby improving calibration under volatility-specific losses, and the framework can be extended to multi-asset and multi-horizon risk forecasting.
Downloads
References
[1] Engle, Robert F. “Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of United Kingdom Inflation.” Econometrica, vol.~50, no.~4, 1982, pp.~987–1007. DOI: https://doi.org/10.2307/1912773
[2] Bollerslev, Tim. “Generalized Autoregressive Conditional Heteroskedasticity.” Journal of Econometrics, vol.~31, no.~3, 1986, pp.~307–327. DOI: https://doi.org/10.1016/0304-4076(86)90063-1
[3] Nelson, Daniel B. “Conditional Heteroskedasticity in Asset Returns: A New Approach.” Econometrica, vol.~59, no.~2, 1991, pp.~347–370. DOI: https://doi.org/10.2307/2938260
[4] Glosten, Lawrence R., Ravi Jagannathan, and David E. Runkle. “On the Relation between the Expected Value and the Volatility of the Nominal Excess Return on Stocks.” The Journal of Finance, vol.~48, no.~5, 1993, pp.~1779–1801. DOI: https://doi.org/10.1111/j.1540-6261.1993.tb05128.x
[5] Hansen, Bruce E. “Autoregressive Conditional Density Estimation.” International Economic Review, vol.~35, no.~3, 1994, pp.~705–730. DOI: https://doi.org/10.2307/2527081
[6] Hochreiter, Sepp, and J{"urgen Schmidhuber. “Long Short-Term Memory.” Neural Computation, vol.~9, no.~8, 1997, pp.~1735–1780. DOI: https://doi.org/10.1162/neco.1997.9.8.1735
[7] Andersen, Torben G., et al. “Modeling and Forecasting Realized Volatility.” Econometrica, vol.~71, no.~2, 2003, pp.~579–625. DOI: https://doi.org/10.1111/1468-0262.00418
[8] Corsi, Fulvio. “A Simple Approximate Long-Memory Model of Realized Volatility.” Journal of Financial Econometrics, vol.~7, no.~2, 2009, pp.~174–196. DOI: https://doi.org/10.1093/jjfinec/nbp001
[9] Patton, Andrew J. “Volatility Forecast Comparison Using Imperfect Volatility Proxies.” Journal of Econometrics, vol.~160, no.~1, 2011, pp.~246–256. DOI: https://doi.org/10.1016/j.jeconom.2010.03.034
[10] Kristjanpoller, Werner, and Mauro C. Minutolo. “Gold Price Volatility: A Forecasting Approach Using the Artificial Neural Network–GARCH Model.” Expert Systems with Applications, vol.~42, no.~20, 2015, pp.~7245–7251. DOI: https://doi.org/10.1016/j.eswa.2015.04.058
[11] Kim, Ha Young, and Chang Hyun Won. “Forecasting the Volatility of Stock Price Index: A Hybrid Model Integrating LSTM with Multiple GARCH-Type Models.” Expert Systems with Applications, vol.~103, 2018, pp.~25–37. DOI: https://doi.org/10.1016/j.eswa.2018.03.002
[12] Hu, Yan, Jian Ni, and Liu Wen. “A Hybrid Deep Learning Approach by Integrating LSTM-ANN Networks with GARCH Model for Copper Price Volatility Prediction.” Physica A: Statistical Mechanics and its Applications, vol.~557, 2020, article 124907. DOI: https://doi.org/10.1016/j.physa.2020.124907
[13] Micha'nk'ow, Jakub, {Kwiatkowski, and Janusz Morajda. “Combining Deep Learning and GARCH Models for Financial Volatility and Risk Forecasting.” arXiv, 2023, arXiv:2310.01063. https://arxiv.org/abs/2310.01063. DOI: https://doi.org/10.2139/ssrn.4589950
[14] Xu, Zeda, et al. “GARCH-Informed Neural Networks for Volatility Forecasting.” Proceedings of the 5th ACM International Conference on AI in Finance (ICAIF ’24), ACM, 2024, pp.~600–607. DOI: https://doi.org/10.1145/3677052.3698600
[15] Zhao, Pengfei, et al. “From GARCH to Neural Network for Volatility Forecast.” arXiv, 2024, arXiv:2402.06642. https://arxiv.org/abs/2402.06642.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
