Rodolfo Metulini
Tenure Track Assistant Professor (RTD-B) in Statistics for Experimental and Technological Research (SECS/S-02)
University of Bergamo
Below, my personal CV (constantly updated...)
Tenure-Track Assistant Professor (RTD-B) in "Statistics for Experimental and Technological Research" (SECS-S/02) at the Department of Economics of the University of Bergamo.
Principal Investigator (PI) of the PRIN/PNRR project "SIGNUM: Study of mobile phone siGNals for the evalUation of the interconnections between Mobility and the environment in Lombardia"
Phd in "Statistical Methodology for the Scientific Research" obtained in 2013 at the Department of Statistical Sciences "P. Fortunati" - University of Bologna.
Past commitments at Università of Salerno (Assistant Professor, July 2019 - July 2022), University of Brescia (Post-Doc, Lug 2016 - Giu-2019), S.Anna Pisa (Post-Doc, Sep 2015 - Jul 2016) and IMT School for Advanced Studies (Post-Doc, Jun 2013 - Sept 2015).
My research activity pertains with the statistical analysis of movements:
In Sports Analytics, where, to determine the probabilty to win the game and the players' marginal utility, the comprehension of the complex dynamic of the players' movements on the court is of fundamental importance. I contribute by matching Statistical Learning with Game Theory methods to assess the role of players movements and their position on the court
In Traffic Management for urban areas, where, to gather information on origin-destination traffic flows and people movements, I match, analyze and model different sources of mobile phone data. Here, adapted versions of time series models for complex seasonalities are matched with functional data (clustering) approaches to shed lights on the dynamic of traffic flows and their regularities
In International Trade, where, to understand the dynamics of the movement of goods between sectors and between countries, origin-destination and Input-Output matrices are analyzed using the Gravity Model along with a spatial interaction approach and a forecast is obtained by means of an adapted Matrix Completion methods.