April 22, 2022


The extraction and analysis of crime patterns in large cities is a challenging spatiotemporal problem. The number and type of crimes vary considerably across cities, assuming different patterns depending on each particular location’s urban and social characteristics. Urban factors such as population density, the flow of people, parking lots, and socioeconomic conditions strongly influence the patterns and dynamics of crime in each city location. 
In this talk, Dr. Jorge Poco will present data science, visualization, and machine learning tools to identify and understand spatially and temporally crime dynamics. In addition, he will describe some tools capable of exploring specific city locations, which are essential for domain experts to perform their analysis in a bottom-up manner. In this way, we can reveal how urban characteristics related to mobility,  pedestrian behavior, and the presence of public infrastructures can influence the amount and type of crime.
Jorge Poco is an Associate Professor in Computer Science and Data Science at Fundação Getúlio Vargas (FGV), Rio de Janeiro, Brazil. He is also the leader of the Visual Data Science Laboratory at the FGV. In 2020, he was recognized as a Distinguished Young Researcher by the Research Support Foundation of the State of Rio de Janeiro. His research was financed by several research promotion agencies in Peru and Brazil (Concytec, FAPERJ, CNPq, and CAPES) and private companies. Previously, he was an assistant professor at the San Pablo Catholic University in Peru and a research associate at the University of Washington. He received his Ph.D. in Computer Science from New York University and an M.S. in Computer Science from the University of São Paulo. As part of his professional life, he worked in zAgile, Google, Kitware, Oak Ridge National Laboratory, and Xerox Research.
His research has focused on data visualization, data science, and machine learning. He has participated in information visualization, scientific visualization, and visual analytics projects. His works include interdisciplinary collaborations that focus on developing novel visualization methods to enable climate, urban, and crime data analysis. He also has an interest in techniques for automatic chart interpretation.