Vlasios Voudouris is a Data Scientist with expertise in data-driven predictive analytics and risk quantification of financial markets. His primary research  focus is on i) semi-parametric machine learning models; ii) innovative model selection processes and iii) robust diagnostics for systematic trading and risk quantification.  He is the co-author of the book “Flexible Regression and Smoothing: Using GAMLSS in R” [and the associated software in R and Java]. GAMLSS (Generalized  Additive Models for Location Scale and Shape) is about learning from data using semi-parametric supervised machine learning algorithms. Furthermore, Vlasios developed data-driven agent-based models for stress testing scenarios (with an emphasis on commodity markets). His models and tools  are used by a range of organisations. By way of two specific examples: 1) the IMF used GAMLSS for stress testing the U.S. financial System; 2) Vlasios and his colleagues demonstrated a suite of GAMLSS models for the Bank of England (BoE). Using GAMLSS, Vlasios developed a systematic trading model for WTI Crude Oil (NYMEX).  Vlasios holds a Ph.D. from City, University of London.
Education
City, University of London
Areas of Research / Professional Expertise
Data Science, Machine Learning, Statistical Learning, Predictive Analytics, Risk Quantification, Generalized Additive Models, Smoothing