EUVIMEDEUVIMED entdecken
Crossref

A RISK-AWARE HYBRID ENSEMBLE APPROACH FOR AEX INDEX FORECASTING: INTEGRATING APARCH-T VOLATILITY WITH LSTM-CNN-RF ARCHITECTURES

AMAN SHREEVASTAVA, BHARAT KUMAR MEHER, RAMONA BIRAU, VIRGIL POPESCU, SHAHIL RAZA, GABRIELA ANA MARIA LUPU (FILIP), STEFAN MARGARITESCU

Annals of "Constantin Brâncuși" University of Târgu Jiu - Economy Series · 26.02.2026 · 2026 (1) · 7-25

DOI: 10.65631/jes.1.2026.1 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Annals of "Constantin Brâncuși" University of Târgu Jiu - Economy Series, online erschienen am 26.02.2026. Verfasst von AMAN SHREEVASTAVA und 6 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The accurate prediction of financial time-series remains a formidable challenge due to inherent non-linearity, heteroskedasticity, and the presence of "fat-tailed" distributions. This study proposes a novel, risk-augmented hybrid ensemble framework designed to enhance the forecasting precision of the Amsterdam Exchange (AEX) index. Departing from conventional monolithic models, the research methodology integrates an asymmetric power autoregressive conditional heteroskedasticity (APARCH) model with a Student-t distribution to extract robust volatility features. These econometric inputs are subsequently fed into a tripartite deep learning ensemble comprising Long Short-Term Memory (LSTM) networks for temporal dependencies, Convolutional Neural Networks (CNN) for spatial feature extraction, and Random Forest (RF) for non-linear regression refinement. Empirical results demonstrate that the proposed architecture significantly outperforms baseline models, achieving a high predictive accuracy characterized by an $R^{2}$ of 0.9408 and a Mean Absolute Error (MAE) of 4.9542. A critical finding of this research is the significance of the leptokurtic nature of AEX returns (Kurtosis: 12.64); by anchoring the machine learning engine with APARCH-derived conditional volatility, the model effectively mitigates the impact of market noise and transient shocks. Furthermore, Value-at-Risk (VaR) backtesting validates the model’s

Zitieren

APA

SHREEVASTAVA, A., MEHER, B. K., BIRAU, R., POPESCU, V., RAZA, S., (FILIP), G. A. M. L., & MARGARITESCU, S. (2026). A RISK-AWARE HYBRID ENSEMBLE APPROACH FOR AEX INDEX FORECASTING: INTEGRATING APARCH-T VOLATILITY WITH LSTM-CNN-RF ARCHITECTURES. Annals of "Constantin Brâncuși" University of Târgu Jiu - Economy Series, 2026(1), 7-25. https://doi.org/10.65631/jes.1.2026.1

Vancouver

SHREEVASTAVA A, MEHER BK, BIRAU R, POPESCU V, RAZA S, (FILIP) GAML, et al. A RISK-AWARE HYBRID ENSEMBLE APPROACH FOR AEX INDEX FORECASTING: INTEGRATING APARCH-T VOLATILITY WITH LSTM-CNN-RF ARCHITECTURES. Annals of "Constantin Brâncuși" University of Târgu Jiu - Economy Series. 2026;2026(1):7-25. doi:10.65631/jes.1.2026.1

BibTeX
@article{SHREEVASTAVA2026,
  author = {SHREEVASTAVA, AMAN and MEHER, BHARAT KUMAR and BIRAU, RAMONA and POPESCU, VIRGIL and RAZA, SHAHIL and (FILIP), GABRIELA ANA MARIA LUPU and MARGARITESCU, STEFAN},
  title = {A RISK-AWARE HYBRID ENSEMBLE APPROACH FOR AEX INDEX FORECASTING: INTEGRATING APARCH-T VOLATILITY WITH LSTM-CNN-RF ARCHITECTURES},
  journal = {Annals of "Constantin Brâncuși" University of Târgu Jiu - Economy Series},
  year = {2026},
  volume = {2026},
  number = {1},
  pages = {7--25},
  doi = {10.65631/jes.1.2026.1}
}
Kostenlos starten →