“…Over the last several decades, significant progress has been made in modelling the volatilities of multivariate stock market returns. Nowadays, there are four main approaches: multivariate generalised autoregressive conditional heteroskedasticity (MGARCH) models (Engle, 2002;Engle and Kroner, 1995), multivariate stochastic volatility (MSV) models (Chib et al, 2009) realised covariance models (Bollerslev et al, 2018;Jin and Maheu, 2013), and machine learning (ML) algorithms (Bejger and Fiszeder, 2021;Fiszeder and Orzeszko, 2021). All of these approaches have some strengths and weaknesses, and the choice between them depends on the specific characteristics of the data, the objectives of the analysis, and the trade-offs between modelling flexibility and computational complexity.…”