Interplay of Volatility and Geopolitical Tensions in Clean Energy Markets: A Comprehensive GARCH-LSTM Forecasting Approach

Hatem Brik and Jihene El Ouakdi
Additional contact information
Jihene El Ouakdi: University of Manouba, Higher School of Digital Economy, GEF2A Lab, Tunisia

International Journal of Energy Economics and Policy, 2024, vol. 14, issue 4, 92-107

Abstract: In an era dominated by increasing global challenges and market volatilities, this study, firstly, embarks on an in-depth exploration of volatility transmission across clean energy stocks, crude oil and financial markets, emphasizing the underlying currents of geopolitical tensions. By using the advanced Multivariate Dynamic Conditional Correlation (MV-DCC) GARCH model, we unravel a landscape where volatility spillovers exhibit a distinct bidirectional nature, and geopolitical risk exerts a substantial impact, cascading from the oil market to financial markets and ultimately to clean energy stocks. Our findings underline the strategic importance of overweighting clean energy assets in a dual-asset portfolio that includes oil and financial equities to enhance investment strategies in turbulent market conditions. Secondly, we investigate the predictive power of oil and market-implied volatilities in forecasting clean energy market volatility by introducing a novel approach that melds the robustness of GARCH models with the flexibility of Long Short-Term Memory (LSTM) networks, creating an innovative hybrid GARCH-LSTM framework. The empirical results demonstrate that this hybrid model significantly outstrips the predictive capabilities of traditional standalone models. Notably, while oil and market-implied volatilities substantially enhance prediction accuracy, the inclusion of historical data does not yield additional predictive value. The implications of our research extend beyond the analytical domain, resonating with financial practitioners and environmentally conscious investors who seek precision in valuation and foresight in market trends. For policymakers, the insights provided offer strategic guidance for developing robust clean energy policies. Overall, our research contributes a fresh perspective to the discourse on renewable energy investment, volatility forecasting, and the interplay between market dynamics and geopolitical risks.

Keywords: Clean Energy; Generalized Autoregressive Conditional Heteroskedasticity Models; Hybrid Generalized Autoregressive Conditional Heteroskedasticity-Long Short-Term Memory Framework; Volatility Forecasting; Portfolio Management (search for similar items in EconPapers)
JEL-codes: C53 C58 G11 G13 Q47 (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.econjournals.com/index.php/ijeep/article/download/16075/7971 (application/pdf)
https://www.econjournals.com/index.php/ijeep/article/view/16075 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eco:journ2:2024-04-9

Access Statistics for this article

International Journal of Energy Economics and Policy is currently edited by Ilhan Ozturk

More articles in International Journal of Energy Economics and Policy from Econjournals
Bibliographic data for series maintained by Ilhan Ozturk ().