Recurrent Neural Network GO-GARCH Model for Portfolio Selection

Abstract We develop a hybrid model of multivariate volatility that uses recurrent neural networks to capture the conditional variances of latent orthogonal factors in a GO-GARCH framework. Our approach seeks to balance model flexibility with ease of estimation and can be used to model conditional covariances of a large number of assets. The model performs favourably in comparison with relevant benchmark models in a minimum variance portfolio (MVP) scenario.