A1027
Title: Deep learning enhanced multivariate GARCH
Authors: Minh-Ngoc Tran - University of Sydney (Australia)
Chao Wang - The University of Sydney (Australia) [presenting]
Chen Liu - The University of Sydney (Australia)
Abstract: A novel volatility modeling framework that integrates deep learning into multivariate GARCH processes through a long short-term memory (LSTM) enhanced BEKK (LSTM-BEKK) model is introduced. By combining the flexibility of recurrent neural networks with the econometric structure of BEKK models, the approach is designed to better capture nonlinear, dynamic, and high-dimensional dependence structures in financial return data. The proposed model addresses key limitations of traditional multivariate GARCH-based methods, particularly in capturing persistent volatility clustering and asymmetric co-movement across assets. Leveraging the data-driven nature of LSTMs, the framework adapts effectively to time-varying market conditions, offering improved robustness and forecasting performance. Empirical results across multiple equity markets confirm that the LSTM-BEKK model achieves superior performance in terms of risk modeling and out-of-sample portfolio stability. These findings highlight the potential of hybrid econometric-deep learning models in advancing financial risk management and multivariate volatility forecasting.
