Dr Roman Marchant (University of Sydney)
Bachelor of Engineering (Electrical, Electronics and Communications)
PhD (Artificial Intelligence)
Dr Roman Marchant completed a PhD at the School of Information Technologies, University of Sydney in 2015. His current research at DARE explores developing new data science techniques to answer complex questions in the social sciences, currently focusing on predicting crime and understanding criminal behaviour.
His area of expertise is Sequential Bayesian Optimisation (SBO), which is a novel probabilistic method for optimal sequential decision making under uncertainty that maximises long-term reward. Although SBO has been readily applied to robotics and environmental monitoring, it can be applied to any optimisation problem.
Roman is currently exploring the application of SBO to increase the efficiency and reduce bias in predictive policing. Throughout his career, Dr Marchant has received several awards, which include the Google Publication Prize 2013, Best Presentation at the University of Sydney Student Conference 2013 and 2014.
He was selected by the Chilean Government for a PhD scholarship in 2011 and then received a Top-up scholarship from NICTA in 2012. Roman has undertaken a number of projects developing data science models to understand real world problems including work with NSW Police to understand juvenile crime and on the effectiveness of lock-out laws in Sydney to curb alcohol related assaults.