Wednesday, 13 May 2026 Francesco Ricci: Simulation-Based Evaluation of Trustworthy Recommender Systems
You are invited to a lecture by Francesco Ricci, which will take place on Monday, May 25, at 4:00 PM in the lecture room VP3, UP FAMNIT.
Francesco is a senior professor in Computer Science at the Free University of Bozen-Bolzano (UNIBZ), Italy. He is a member of the UNIBZ Competence Center on Sustainability and a member of the Steering Committee of the Digital Humanism Initiative, TUW, Vienna.
His current research interests focus on the usage of Artificial Intelligence techniques, such as Recommender Systems and intelligent agents, in supporting human collaboration with AI, and ultimately improving users' decision-making processes and well-being. He is interested in building systems that can help groups and individuals to make more rational and fair decisions in complex and context-dependent scenarios, such as news and tourism.
He is the author of more than 250 highly cited, refereed publications. He coedited the Recommender Systems Handbook, a reference publication, and served as president of the steering committee of the ACM conference on RSs.
Recommender systems (RSs) are personalized artificial intelligence (AI) tools routinely used by online platforms to promote algorithmically selected news, posts, music, travel, and videos. This talk will focus on the goal of making these systems more trustworthy, ensuring they better serve the various stakeholders interested in their functionality, especially the end users and the providers of the recommended items. A novel type of user/system interaction simulation framework, proposed as an approach to assess RSs performance, will therefore be presented.
Compared to the standard train/test ML evaluation approach, this framework enables a better estimation of the longitudinal and multidimensional effects (positive and negative) that an RS can have. The core idea is to more faithfully simulate users' reactions to the recommendations produced by the tested RS by relying on a calibrated algorithmic model of how users make their choices, i.e., select items among the recommended ones. This approach departs from the standard ML testing mechanism that leverages testing data sampled from historical user/ system interaction logs, which, unfortunately, were acquired when users interacted with unknown and different RSs.
The application and usefulness of this evaluation approach will be exemplified in a particular case study: sustainable tourism management, specifically, how to mitigate overtourism, respect local communities, and still satisfy tourist preferences.
