I didn't start out chasing algorithms — I started out chasing curiosity about how the world works, back when I was a kid obsessed with science. Life (and a bit of peer influence) nudged me toward business and economics instead, and I followed that path through high school and into an undergrad in Economics and Business at Ca' Foscari University of Venice, where I held a merit scholarship as one of only 100 students selected that year. Financial Economics, Corporate Finance, Micro/Macroeconomics, European Public and Private Law — solid foundations, but my head kept wandering elsewhere.
In my final year, I gave in and started taking extra courses in statistics, computer science, and data analysis. Non potevo più resistere — I couldn't resist any longer. I enjoyed it enough to brute-force my way into an MSc in Data Science, and right now I'm on the final stretch: thesis left, and what a journey it's been.
The MSc gave me the theoretical foundations. Key coursework included Statistical Machine Learning, Bayesian Inference, Algorithmic Data Minining, Neural Networks for Data Science, Advanced ML, Cloud Computing, and Big Data Computing. Now I'm deliberately pointing myself at deployment. I am actively learning ML engineering, system design, and hands-on cloud deployment to bridge the gap between local notebooks and production scale. Building upon these core deployment fundamentals, my next frontier is Generative AI - engineering Large Language Models from scratch and building agentic applications. A poco a poco.
TiM x Sapienza — Machine Unlearning: Making Models Forget Ranked 6th out of 25 teams, and came out having learned state-of-the-art machine unlearning techniques.
The Best Books of All Time — data analysis and algorithmic problem-solving across two large book/author datasets, using Python, Pandas, command-line scripting, Apache Spark, Dask, and AWS EC2.
Scraping Master's Degrees & Building a Search Engine from Scratch — scraped a website listing master's degrees, then built a search engine from its mathematical foundations up.
Similarity in Customers & Clustering Movies — LSH for recommendation systems, applied to customer segmentation and movie clustering.
Car Insurance Analysis and Claim Prediction — predicting insurance claims with XGBoost, Logistic Regression, and SVM, exploring how ML sharpens risk assessment and pricing accuracy.
Predicting Apple Inc. Stock Returns — forecasting quarterly positive/negative stock returns from 2009–2024 using stock data, company features, and economic indicators.
USA Airport Flight Analysis — applying network analysis theory to real airport flight data.
CPU Thermal-Event Prediction (Apple Silicon) — predicting whether a Mac's CPU will hit a distress temperature within the next two minutes, using only telemetry the OS already reports.
Dozens of certifications from Coursera — including courses from Google, the University of Illinois, and Harvard — and from DataCamp, covering Python, SQL, data analysis, machine learning, and deep learning.
Grazie per la visita — thanks for stopping by.