Hello there, this is Andrea! I am from Sarzana, Italy, and I am currently a postdoc at University of Pisa focusing on teaching ML models to learn what they do not know.
I obtained a MSc in Economics and Social Sciences from Bocconi University (Milan, Italy) in 2018 and a PhD in Data Science from Scuola Normale Superiore (Pisa, Italy) in 2024.
During my PhD, I worked under the supervision of professor Salvatore Ruggieri and Francesca Chiaromonte.
My thesis focused on Selective Prediction, a framework that extends supervised learning by allowing ML models to abstain from making predictions on examples that are too hard to predict. This is a crucial feature for real-world applications, where the cost of making a mistake can be high.
My research interests currently include abstaining systems, deferring systems, causal inference and fair AI.
Please visit my Google Scholar for an updated list of my publications, and my GitHub for updated repositories.
When I am not working, I enjoy doing a bunch of things, including living surrounded by a wood with my partner Caroline, bothering my family with random arguments, failing at bouldering, acting for Compagnia Ordinesparso, anything related to football and fantacalcio (fantasy football).