I am Chris Carmona, a doctoral researcher in Statistical Machine Learning at the University of Oxford, advised by Prof. Geoff Nicholls. My research is aimed to developing novel inferential methods and applied probabilistic modelling.
Recently, I have been working on two main topics: 1) Partially Modular Inference (PMI), a Bayesian method to learn from multiple sources of information under difficult conditions, such as model misspecification and copious missing data; and 2) Probabilistic models for dynamic relational data, with applications to large datasets of financial transactions.
I hold a master degree in Applied Statistics from UC Berkeley, and have also been lecturer at the National University of Mexico in subjects on Statistical Learning and Actuarial Modelling.
Besides my academic track, I have collaborated in public and private institutions. I’m currently a Data Researcher at FNA, where I design and implement quantitative methods for financial networks. I’ve held several positions at the Central Bank of Mexico, including Senior Financial Researcher, and Head of the Financial Risk Office within the Directorate of Risk Management. I’ve also participated in consultancy projects to estimate the official poverty indicators in Mexico for CONEVAL.
DPhil in Statistics, 2020
University of Oxford
MA in Statistics, 2014
University of California, Berkeley
BSc in Actuarial Sciences, 2009
National University of Mexico (UNAM)