Machine learning algorithms are widely used in the recommender systems for personalizing content recommendations based on user preferences. However, these algorithms can inadvertently promote certain producers while overlooking others, raising ethical and societal concerns about fairness and representation. This work aims to create fairer recommendation algorithms that balance user preferences with content producer welfare. Addressing the challenges of defining fairness for ranked recommendations and preserving computational efficiency, we propose a framework grounded in social choice theory. This framework guides the development of new recommendation methods that fairly distribute exposure to content producers without compromising rcommen...
International audienceMost of product recommender systems are based on artificial intelligence algor...
There is an increasing focus on fairness in recommender systems, with a growing body of literature o...
There is an increasing focus on fairness in recommender systems, with a growing body of literature o...
Nowadays, it is widely recognized that algorithms risk to reproduce and amplify human bias that hist...
International audienceMost of product recommender systems in marketing are based on artificial intel...
International audienceMost of product recommender systems in marketing are based on artificial intel...
Algorithmic decision-making has become ubiquitous in our societal and economic lives. With more and ...
Recommender systems are one of the most widely used services on several online platforms to suggest ...
We increasingly depend on a variety of data-driven algorithmic systems to assist us in many aspects ...
We increasingly depend on a variety of data-driven algorithmic systems to assist us in many aspects ...
In this thesis we propose semantic-social recommendation algorithms, that recommend an input item to...
Machine learning algorithms are increasingly used by decision making systems that affect individual ...
Collaborative filtering is a method that aims at building automatically personalized filters by usin...
In this thesis, we address the scalability problem of recommender systems. We propose accu rate and ...
In this thesis, we address the scalability problem of recommender systems. We propose accu rate and ...
International audienceMost of product recommender systems are based on artificial intelligence algor...
There is an increasing focus on fairness in recommender systems, with a growing body of literature o...
There is an increasing focus on fairness in recommender systems, with a growing body of literature o...
Nowadays, it is widely recognized that algorithms risk to reproduce and amplify human bias that hist...
International audienceMost of product recommender systems in marketing are based on artificial intel...
International audienceMost of product recommender systems in marketing are based on artificial intel...
Algorithmic decision-making has become ubiquitous in our societal and economic lives. With more and ...
Recommender systems are one of the most widely used services on several online platforms to suggest ...
We increasingly depend on a variety of data-driven algorithmic systems to assist us in many aspects ...
We increasingly depend on a variety of data-driven algorithmic systems to assist us in many aspects ...
In this thesis we propose semantic-social recommendation algorithms, that recommend an input item to...
Machine learning algorithms are increasingly used by decision making systems that affect individual ...
Collaborative filtering is a method that aims at building automatically personalized filters by usin...
In this thesis, we address the scalability problem of recommender systems. We propose accu rate and ...
In this thesis, we address the scalability problem of recommender systems. We propose accu rate and ...
International audienceMost of product recommender systems are based on artificial intelligence algor...
There is an increasing focus on fairness in recommender systems, with a growing body of literature o...
There is an increasing focus on fairness in recommender systems, with a growing body of literature o...