Research

My research lies within the fields of machine learning, causality, and ethical AI. I’m mainly interested in causal notions of fairness, structural counterfactuals, and knowledge representation.

Conference Papers

“Can We Trust Fair-AI?” Salvatore Ruggieri, Jose M. Alvarez, Andrea Pugnanna, Laura State, Franco Turini. AAAI Conference on Artificial Intelligence, 2023. [paper]

Journal Papers

“Predicting and explaining employee turnover intention.” Matilde Lazzari, Jose M. Alvarez, and Salvatore Ruggieri. International Journal of Data Science and Analytics (IJDSA), 2022. [paper]

Working Papers

Jose M. Alvarez, Salvatore Ruggieri. “Counterfactual Situation Testing: Uncovering Discrimination under Fairness given the Difference.” Under submission. [arXiv][code]

Jose M. Alvarez, Kristen M. Scott, Salvatore Ruggieri, Bettina Berendt. “Domain Adaptive Decision Trees: Implications for Accuracy and Fairness.” Under submission. [arXiv][code]

Carlos Mougan, Jose M. Alvarez, Gourab K. Patro, Salvatore Ruggieri, and Steffen Staab. “Fairness implications of encoding protected categorical attributes.” [paper]

Work in Progress

“The Initial Ordering Ranking Problem” with Salvatore Ruggieri.

Invited talks, presentations, and workshops

• IMS International Conference International Conference on Statistics and Data Science; Poster Session; Florence, Italy; December 2022.
• NeurIPS 2022 Workshop on Algorithmic Fairness through the Lens of Causality and Privacy; Poster Session; New Orleans, USA; December 2022.
• Comete Workshop on Ethical AI; Invited Speaker; Palaiseau, France; September 30, 2022.
• ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT); Doctoral Consortium; Seoul, South Korea; June 2022.
• European Workshop on Algorithmic Fairness (EWAF); Lightning Round Presentation; Zurich, Switzerland; June 2022.