Experience

 
 
 
 
 
May 2018 – August 2018
Yorktown Heights, NY

AI Research Intern

IBM Research

Convolutional deep neural networks pruning for multiple objectives, in PyTorch.
 
 
 
 
 
October 2014 – June 2016
London

Game Analyst - Data Science Team

Zynga (Naturalmotion LTD)

Data processing and modeling for live and in development games, mainly Dawn of Titans. Main projects:

  • Behavior-based clustering for the user base;
  • Supervised classification task mainly targeting user retention and monetization;
  • Automatic KPI reporting for company-wide distribution;
  • ETL data pipelines in Python for live internal dashboards.

Selected Publications

We propose Lebesgue Regression, a non-parametric high-dimensional regression method that gives prediction sets instead of a single predicted value. Our method as a theoretically guaranteed coverage and automatically cautious - i.e. outliers and extrapolations returns empty prediction sets.
In NeurIPS 2018 Workshop, 2018

We have developed a Bayesian hierarchical model of the full distance ladder to assess the H0 discrepancy between the local distance ladder and the cosmic microwave background via a Bayesian model camparison. Our approach does not realy not rely on Gaussian distributions and allows outliers to be modelled without arbitrary data cuts. We find at worst ~10:1 odds against ΛCDM, considering the Planck 2015 XIII data and regardless of outlier treatment.
In MNRAS, 2018

Skills

Statistics

Machine Learning

Data Analysis

R

Python

2.7 - 3.6

SQL

MySQL - Vertica SQL

Projects

A fully data-drive statistical framework to create confidence bands around tropical cyclone paths.

Teaching

Aug 2016

Advising and Mentoring

Department of Statistics & Data Science, Carnegie Mellon University

Supervised research carried out by undergraduates students in different occasions:

  • Summer Undergraduate Research Experience (SURE, Summer 2017) - Advised a team working on automatic typing discrimination and handwritten signature analysis
  • Data Science Initiative (DSI) Fellow (Fall 2018) - Advised two undergraduate teams working with Principal Financial.
Aug 2016

Teaching Assistant

Department of Statistics & Data Science, Carnegie Mellon University

In-class tutorials, office hours and grading for the following classes:

  • 36-401 Modern Regression
  • 36-402 Undergraduate Advanced Data Analysis
  • 36-492 Financial Data Science I
  • 36-493 Financial Data Science II
  • 36-315 Statistical Graphics and Visualization (Head TA)
  • 36-750 Statistical Computing - PhD Level
  • 36-708 Statistical Methods in Machine Learning - PhD Level
Jul 2012 – Jul 2016

Lecturer

Campus FMS

Taught a multitude of classes during summer and winter courses for high school students, located in the Turin area (Italy). Courses and tutorials included:

  • Mathematical analysis in one, two and higher dimensions
  • Game theory
  • Probability theory and Statistics
  • Dynamical systems
  • Mathematical Logic

Honors

Nov 2017

Citadel Data Open Datathon at Carnegie Mellon University

1st Prize

Competed and won with fellow students Alan Mishler, Kwhangho Kim, and Chirag Nagpal (550+ student applications, around 125 students selected to compete).
Jan 2013

Full Scholarship - 2011, 2012, 2013

Scuola of Studi Superiori ‘Ferdinando Rossi’

Scholarship covering tuition fees, annual bursary and living expenses via the Scuola of Studi Superiori ‘Ferdinando Rossi’ and ‘Compagnia di San Paolo’.
Oct 2012

Alfaclass Mathematics Team Competition

1st Prize

Mathematics team competition within the Mathematics summer camp ‘Alfaclass’, held via invitation only based on academic merit.

Contact Me

  • 5000 Forbes Avenue, Pittsburgh, PA, 15213