Sasin’s Assistant Professor Wantanee Poonvoralak, Ph.D., DIC., CStat, presented her paper titled, “Can Bayesian GARCH Models be Reparameterized and Constrained for Better Forecasting in Volatile Financial Markets after COVID-19?” at the 2024 Quantitative Methods in Finance (QMF) Conference. The event is being held from December 17 to 20, 2024, at the University of Technology Sydney (UTS) in Sydney, Australia. Dr. Wantanee’s research focuses on enhancing Generalized Autoregressive Conditional Heteroscedastic (GARCH) models through reparameterization and the introduction of constraints. By employing Bayesian computation via the Markov Chain Monte Carlo (MCMC) approach, her study aims to better capture the persistence of volatility in highly turbulent foreign exchange (FX) markets, particularly in the aftermath of the COVID-19 crisis. A key aspect of this research is the addition of a new constraint to the GARCH model, designed to mitigate high kurtosis—a common challenge in financial time series. The study also explores reparameterized GARCH and Student t-GARCH models to reduce autocorrelation in sampling chains, thereby improving estimation accuracy. This novel approach seeks to enhance computational efficiency and offer more reliable tools for financial market forecasting.