María Fernanda Sobrino is a professor and researcher specializing in data science, machine learning, and computational methods for the study of violence, crime, and political processes. She received her PhD from Princeton University and completed a postdoctoral fellowship at the Harris School of Public Policy at the University of Chicago. Her research focuses on the use of large-scale administrative and digital data, combined with statistical modeling and artificial intelligence, to understand, predict, and prevent phenomena such as gender-based violence, human trafficking, organized crime, and electoral disinformation.
Her recent work includes mapping criminal organizations across municipalities in Mexico and Colombia; studying the effects of the opioid crisis on competition between drug cartels in Mexico; analyzing the relationship between market structure and violence in drug markets; tracking political violence against candidates in Mexico; and measuring which types of information most effectively help migrants reduce risks while crossing through Mexico. Her research agenda sits at the intersection of machine learning, causal inference, and public policy, and is driven by the goal of producing rigorous, data-driven evidence to improve public decision-making in violent and high-risk contexts.