Advancing Stock Price Forecasting Through Hybrid Deep Learning and Volatility Modeling Techniques
Boletim da Sociedade Paranaense de Matemática · 06.11.2026 · 44 · 1-8
DOI: 10.5269/bspm.84095 ↗Kurz gefasst
Fachartikel in der Zeitschrift Boletim da Sociedade Paranaense de Matemática, online erschienen am 06.11.2026. Verfasst von Srinivasulu Akasam und 4 weiteren Autor:innen. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Market forecasting becomes essential when investors make decisions about investment choices under fluctuating market conditions. In this study, we analyze the predictive ability of advanced models SVR, GJR-GARCH-SVR, LSTM, and GJR-GARCH-LSTM to forecast the price behavior of the NASDAQ Composite Index using historic stock prices (2010-2024). GJR- GARCH-LSTM has shown the highest level of accuracy with MAPE of 0.66\% and R-squared of 0.9928. Hybrid models perform better than traditional models, showing that hybrid AI models can be effective tools in predicting future events by identifying non-linear trends and capturing asymmetries in stock prices. The ARIMA model detects linear trends in the stock prices. On the other hand, GJR-GARCH accounts for volatility clusters and negative return asymmetries. Our results suggest that all models produce good forecasts with high accuracy rates, but LSTM based models produce exceptionally accurate results.
Zitieren
APA
Akasam, S., Swetha, V., Jayanthi, P., Reddy, A. A. K., & Reddy, V. S. N. (2026). Advancing Stock Price Forecasting Through Hybrid Deep Learning and Volatility Modeling Techniques. Boletim da Sociedade Paranaense de Matemática, 44, 1-8. https://doi.org/10.5269/bspm.84095
Vancouver
Akasam S, Swetha V, Jayanthi P, Reddy AAK, Reddy VSN. Advancing Stock Price Forecasting Through Hybrid Deep Learning and Volatility Modeling Techniques. Boletim da Sociedade Paranaense de Matemática. 2026;44:1-8. doi:10.5269/bspm.84095
BibTeX
@article{Akasam2026,
author = {Akasam, Srinivasulu and Swetha, V. and Jayanthi, P. and Reddy, A. Anil Kumar and Reddy, V. Shiva Narayana},
title = {Advancing Stock Price Forecasting Through Hybrid Deep Learning and Volatility Modeling Techniques},
journal = {Boletim da Sociedade Paranaense de Matemática},
year = {2026},
volume = {44},
pages = {1--8},
doi = {10.5269/bspm.84095}
}
EUVIMED