Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

A Comparative Study of GARCH, Stochastic Volatility, and Hybrid LSTM Models across market regimes

Christopher, David LU (2026) STAH11 20252
Department of Statistics
Abstract
This study examines whether the canonical stochastic volatility (SV) model outperforms the standard GARCH(1,1) model across different market regimes, and whether relatively simple hybrid LSTM extensions improve forecasting accuracy. Using daily data from the Dow Jones, S&P 500, and FTSE 100 indices, volatility forecasts are evaluated on the stressed exogenous COVID-19 crisis, as well as a calm market period. The results indicate that model performance depends on the market regime. During
the stressed COVID-19 period, the GARCH(1,1) consistently achieves slightly lower forecasting errors compared to the SV model. In calmer
market conditions, forecasting errors are smaller overall and no specific
model demonstrates a clear advantage over... (More)
This study examines whether the canonical stochastic volatility (SV) model outperforms the standard GARCH(1,1) model across different market regimes, and whether relatively simple hybrid LSTM extensions improve forecasting accuracy. Using daily data from the Dow Jones, S&P 500, and FTSE 100 indices, volatility forecasts are evaluated on the stressed exogenous COVID-19 crisis, as well as a calm market period. The results indicate that model performance depends on the market regime. During
the stressed COVID-19 period, the GARCH(1,1) consistently achieves slightly lower forecasting errors compared to the SV model. In calmer
market conditions, forecasting errors are smaller overall and no specific
model demonstrates a clear advantage over the other. The hybrid models
are also evaluated across both regimes. The GARCH(1,1)-LSTM specification improves forecasting in several cases, although the gains are comparatively small. In contrast, the SV-LSTM hybrid does not outperform
the baseline SV model in any of the datasets. Overall, the findings suggest that hybrid volatility models are not universally superior and that
forecasting performance is closely linked to model structure, market characteristics, and the complexity of the hybrid specification. (Less)
Please use this url to cite or link to this publication:
author
Christopher, David LU
supervisor
organization
course
STAH11 20252
year
type
M2 - Bachelor Degree
subject
keywords
GARCH(1, 1) Hybrid Models LSTM Hybrid LSTM Stochastic volatility Volatility modelling Financial statistics
language
English
id
9225784
date added to LUP
2026-05-26 13:13:41
date last changed
2026-05-26 13:13:41
@misc{9225784,
  abstract     = {{This study examines whether the canonical stochastic volatility (SV) model outperforms the standard GARCH(1,1) model across different market regimes, and whether relatively simple hybrid LSTM extensions improve forecasting accuracy. Using daily data from the Dow Jones, S&P 500, and FTSE 100 indices, volatility forecasts are evaluated on the stressed exogenous COVID-19 crisis, as well as a calm market period. The results indicate that model performance depends on the market regime. During
the stressed COVID-19 period, the GARCH(1,1) consistently achieves slightly lower forecasting errors compared to the SV model. In calmer
market conditions, forecasting errors are smaller overall and no specific
model demonstrates a clear advantage over the other. The hybrid models
are also evaluated across both regimes. The GARCH(1,1)-LSTM specification improves forecasting in several cases, although the gains are comparatively small. In contrast, the SV-LSTM hybrid does not outperform
the baseline SV model in any of the datasets. Overall, the findings suggest that hybrid volatility models are not universally superior and that
forecasting performance is closely linked to model structure, market characteristics, and the complexity of the hybrid specification.}},
  author       = {{Christopher, David}},
  language     = {{eng}},
  note         = {{Student Paper}},
  title        = {{A Comparative Study of GARCH, Stochastic Volatility, and Hybrid LSTM Models across market regimes}},
  year         = {{2026}},
}