Akademik Veri Yönetim Sistemi
EGE ACADEMIC REVIEW, cilt.26, sa.1, 2026 (ESCI, TRDizin)
The successful modeling and forecasting of volatility, which is the most important element of risk indicators, minimizes financial uncertainties. Classical volatility models are insufficient to forecast structural changes in economic variables. Hybrid models that integrate the benefits of several model architectures have become more significant as the amount of neural network-based research has increased recently. The purpose of the research is to show that mixed models are more accurate and consistent when it comes to predicting variable volatility. For this purpose, the return volatility of the Borsa Istanbul 100 index was modeled, and forecasting performance results were compared with hybrid models. According to the findings, the best forecasting performance was achieved with hybrid structures containing the exponential GARCH-Artificial Neural Networks (MSEGARCH-ANN) combination. It can be said that hybrid models are superior in the risk analysis of volatile financial instruments and in the estimation of macroeconomic variables in general.