RecSys Lab @Polimi is a research group at Politecnico di Milano that researches on the next generation of smart technologies with particular application in Recommender Systems. The group is part of the RecSys community, which is an international forum who annually meet at RecSys conference.
RecSys Lab @Polimi brings together the different views toward recommender systems, namely, Machine Learning, Signal Processing, Human Computer Interaction, Psychology, and Aesthetics, by incorporating these different disciplines to develop new ideas that ultimately lead to new recommender systems.
There are several lines of research, currently pursued by RecSys Lab @Polimi group, mostly within the field of recommender systems but also including performance autotuning and applied quantum machine learning. See the People page for more information.
NEWS: Check the call for papers of our Workshop on Learning and Evaluating Recommendations with Impressions, that will be held at RecSys2023 this September.
NEWS: The call for PhD starting in november 2023 is now open and can be accessed here, the deadline to submit your application is on may 26. If you are interested to work with us get in touch! Further information are available in Student FAQ – Work with us.
NEWS: Our paper “Towards Feature Selection for Ranking and Classification Exploiting Quantum Annealers” has been accepted as a SIGIR 2022 Perspective paper.
NEWS: Politecnico di Milano’s team, coordinated by Maurizio Ferrari Dacrema, Cesare Bernardis and Fernando Benjamin Perez Maurera of our research group, won the first place of the academic part of the RecSys Challenge 2021, sponsored by Twitter. See the news here.
NEWS: Check the Quantum Computing Lab and our Phd Course on Applied Quantum Machine Learning @ PoliMi
NEWS: Amazon Personalize, a machine learning service that provides recommendation models, has added Hierarchical Recurrent Neural Network (HRNN), which our research group contributed to develop. For more details see the article and Amazon HRNN documentation.
NEWS: Our paper “A Troubling Analysis of Reproducibility and Progress in Recommender Systems Research” has been published on ACM TOIS!