EN
This paper introduces and examines a novel realized volaitlity forecasting model that makes use of Long Short-Term Memory (LSTM) neural networks and the risk metric finan cial turbulence (FT). The proposed model is compared to vife alternavtie models, of which two incorporate LSTM neu ral networks and the remaining three include GARCH(1,1), EGARCH(1,1), and HAR models. The results of this paper demonstrate that the proposed model yields statistically significantly more accurate and robust forecasts than all other studied models when applied to stocks with middleto-high volatility. Yet, considering low-volatility stocks, it can only be confidently afirmed that the proposed model yields statistically significantly more robust forecasts rela itve to all other models considered.