Alessandro Fabris

I am a research fellow at Max Planck Institute for Security and Privacy working in the Responsible Computing Group led by Asia Biega, supported by the Alexander von Humboldt Foundation and the FINDHR project on fairness and non-discrimination in algorithmic hiring.

I study algorithmic fairness and auditing in information access systems. My research centers on defining, operationalizing, and measuring fairness, with a focus on domain-specific requirements, and a critical perspective on data management and ethics.

Previously, I spent four years in industry working with IBM and Electrolux. To develop relevant solutions for pressing socio-technical issues, I aim to guide and translate policy into responsible computing practices that can be understood and adopted by practitioners.

News

The 3rd European Workshop on Algorithmic Fairness will take place in Mainz, Germany, on July 1-3, 2024!

I have been granted a Humboldt Research Fellowship to study algorithmic fairness with limited data.

My Ph.D. thesis received the Elena Cornaro Award for gender studies.

We advised five AI providers on compliance at the EU AI Act Grand Challenge.

Our research on discrimination in car insurance was featured on national TV (Rai3) and international press (AlgorithmWatch).

The 2nd European Workshop on Algorithmic Fairness took place in June 2023 and I was a Program Chair. We had a really exciting program (if I may say so myself)!

Our book on quantification is out. Have a look if you're interested in estimators for groups rather than individuals.

I successfully defended my Ph.D. I am now a postdoctoral researcher at Max Planck Institute for Security and Privacy.

I received the IP&M Best Ph.D. Paper Award.

Selected publications

Lazy Data Practices Harm Fairness Research
Jan Simson, Alessandro Fabris, Christoph Kern
(FAccT 2024) The 7th ACM Conference on Fairness, Accountability, and Transparency
[coming soon]

Learning to Quantify
Andrea Esuli, Alessandro Fabris, Alejandro Moreo, Fabrizio Sebastiani
(IRS 2023) The Information Retrieval Series 47, Springer
[PDF] [BIB]

Measuring Fairness Under Unawareness of Sensitive Attributes: A Quantification-Based Approach
Alessandro Fabris, Andrea Esuli, Alejandro Moreo, Fabrizio Sebastiani
(JAIR 2023) Journal of Artificial Intelligence Research, vol 76
[PDF] [BIB]

Pairwise Fairness in Ranking as a Dissatisfaction Measure
Alessandro Fabris, Gianmaria Silvello, Gian Antonio Susto, Asia J. Biega
(WSDM 2023) The 16th ACM International Conference on Web Search and Data Mining
[PDF] [BIB]

Algorithmic Fairness Datasets: the Story so Far
Alessandro Fabris, Stefano Messina, Gianmaria Silvello, Gian Antonio Susto
(DMKD 2022) Data Mining and Knowledge Discovery, vol 36
Webapp released.
[PDF] [BIB]

Tackling Documentation Debt: A Survey on Algorithmic Fairness Datasets
Alessandro Fabris, Stefano Messina, Gianmaria Silvello, Gian Antonio Susto
(EAAMO 2022) The 2nd ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization
[PDF] [BIB]

Algorithmic Audit of Italian Car Insurance: Evidence of Unfairness in Access and Pricing
Alessandro Fabris, Alan Mishler, Stefano Gottardi, Mattia Carletti, Matteo Daicampi, Gian Antonio Susto, Gianmaria Silvello
(AIES 2021) The 4th AAAI /ACM Conference on Artificial Intelligence, Ethics, and Society
National and international press coverage.

National TV: Report Rai3.
[PDF] [BIB]

Gender Stereotype Reinforcement: Measuring the Gender Bias Conveyed by Ranking Algorithms.
Alessandro Fabris, Alberto Purpura, Gianmaria Silvello, Gian Antonio Susto
(IPM 2020) Information Processing & Management, vol 57
IP&M Best Ph.D. Paper Award
[PDF] [BIB]