Blog | Stefano Blando

Presented at MARS @ ETAPS 2026

Tue, 14 Apr 2026 00:00:00 +0000

Last week I presented our paper, “Statistical model checking of the Island Model: an established economic agent-based model of endogenous growth”, at MARS @ ETAPS 2026 in Turin.

This was a particularly meaningful milestone for me: it was the first presentation of my first PhD paper, and also my first international conference.

I am very glad the talk went well. Beyond the presentation itself, I really appreciated the opportunity to discuss the work with professors and researchers in the area and to spend a few days in a workshop environment that I found open, stimulating, and genuinely pleasant.

The paper is co-authored with Giorgio Fagiolo, Daniele Giachini, Andrea Vandin, and Ernest Ivanaj, and focuses on how statistical model checking, and in particular MultiVeStA, can support a more rigorous analysis of the Island Model.

📄
👉
📰

Paper Accepted at MARS @ ETAPS 2026

Fri, 20 Mar 2026 00:00:00 +0000

Our paper, “Statistical model checking of the Island Model: an established economic agent-based model of endogenous growth”, has been accepted at MARS @ ETAPS 2026.

The work is co-authored with Giorgio Fagiolo, Daniele Giachini, Andrea Vandin, and Ernest Ivanaj. The paper shows how statistical model checking and MultiVeStA can be used to make the analysis of the Island Model more rigorous, more automated, and more reproducible, while preserving the economic substance of the original framework.

I presented it in Turin, Italy, on Sunday, April 12, 2026.

📄
👉
🎤

For me, this is one of the clearest examples of the direction I want to push in my PhD work: giving complex simulation models stronger statistical foundations without losing their interpretability.

RiskSentinel for Microsoft AI Dev Days 2026

Sun, 15 Mar 2026 00:00:00 +0000

RiskSentinel is the project I built for the Microsoft AI Dev Days Hackathon 2026.

The core idea was to create a system that could make systemic risk more explorable and more tangible: instead of treating contagion as an abstract output in a paper or a notebook, I wanted an interface where shocks could be launched, propagated, compared, and interpreted in real time.

The project combines network science, contagion modeling, and agentic AI on top of research-grade financial network data covering 210 S&P 500 stocks and 3,081 daily snapshots. Under the hood, it integrates three propagation models, interactive network analytics with Streamlit and Plotly, and an agentic workflow built with Microsoft Agent Framework and Azure OpenAI.

What I like most about this project is that it sits exactly at the boundary between my research interests and practical prototyping: financial networks, complex systems, decision support, and AI agents all in the same tool.

👉
GitHub:
App:

Master Graduation

Fri, 23 Jan 2026 00:00:00 +0000

I am proud to share that on Monday, February 2, 2026, I was awarded the II Level Master in Customer Experience, Statistics, Machine Learning and Artificial Intelligence (CESMA) at the University of Rome Tor Vergata, with a final grade of 110/110 cum laude.

The Thesis

My thesis, titled “Network Topology Analysis and Machine Learning Techniques for Systemic Risk Prediction in U.S. Equity Markets”, explores the application of Graph Neural Networks and complex network theory to identify early warning signals in financial markets.

This work is directly connected to my ongoing research. You can explore the technical details and code in the dedicated sections of this portfolio:

👉
📄

The master provided a strong foundation in advanced statistical methods and AI, which I am now applying to my PhD research at Scuola Superiore Sant’Anna.