Experience

I work in the Corporate Security Modelling team at Bradesco.

Thesis: Network science and machine learning applied to criminal networks

I worked on the project “Network and data science applied to study corruption and organized crime.” My primary goal was to extract meaningful patterns from data on criminal activities, uncovering rules and mechanisms that govern their structure and dynamics.

Thesis: The dynamics of political corruption networks

I investigated the dynamical structure of political corruption networks through the lens of network science and data science. I was able to found surprising results, such as linearity in the evolution of community structures, patterns regarding the growth of recidivist criminals and a coalescence-like process present in the emergence of these networks. Inspired by these and other statistical similarities between the networks, we proposed a model of corruption networks that was able to reproduce the empirical results.

Thesis: Time series analysis via complexity-entropy curves

I proposed a novel parameter (embedding delay) to study time series from several sources. By generalizing the complexity-entropy curve approach, this analysis was useful to find periodic patterns in noisy signals.