🤖 AI Summary
Traditional Gaussian linear models struggle to capture the nonlinearities and heavy-tailed dependencies in transitioning energy financial markets, which arise from abrupt repricing events, high volatility, and heterogeneous macroeconomic shocks. This study proposes a hybrid forecasting framework that uniquely integrates a Student-t vector autoregression—designed to model multivariate heavy-tailed linear dynamics—with recurrent neural network–based residual learning to extract remaining nonlinear predictability. Out-of-sample rolling forecasts on six representative energy ETFs demonstrate that the proposed approach significantly outperforms conventional VAR models, pure machine learning methods, and other hybrid benchmarks. Notably, predictive gains are most pronounced during periods of market stress, such as the COVID-19 crisis and the Ukraine-related energy shocks, revealing an enhanced nonlinear, heavy-tailed, and regime-sensitive forecasting structure inherent to transitional energy markets under extreme conditions.
📝 Abstract
Transition-related financial markets are increasingly exposed to abrupt repricing episodes, elevated volatility, and heterogeneous macro-financial shocks. Under such conditions, conventional Gaussian-linear forecasting frameworks may provide an incomplete representation of the dependence structure linking fossil-energy, renewable-energy, technology, and utility-sector assets. This paper investigates whether transition-related financial returns exhibit residual non-linear predictability after controlling for heavy-tailed multivariate linear dynamics. To address this question, we develop a hybrid forecasting framework combining Student-t Vector Autoregressions with nonlinear recurrent residual learning architectures. The empirical analysis considers six major exchange-traded funds representing broad equity markets and key transition-sensitive sectors. The results reveal substantial departures from Gaussian-linear behavior, including excess kurtosis, volatility clustering, and remaining nonlinear dependence after econometric filtering. Out-of-sample forecasting experiments show that the proposed framework consistently improves predictive accuracy relative to conventional VAR models, standalone machine-learning methods, and alternative hybrid specifications. The forecasting gains become more pronounced during periods of macro-financial stress, particularly during the COVID-19 crisis and the Ukraine-related energy shock. Overall, the findings suggest that transition-related financial systems exhibit regime-sensitive and heavy-tailed predictive dynamics that are insufficiently captured by standard Gaussian-linear models alone.