RecSys CarbonAtor: Predicting Carbon Footprint of Recommendation System Models

Environmental sustainability of AI, or Green AI, is a topic that is getting more and more crucial in the last few years. However, AI systems continue to improve at the cost of huge resources, neglecting the environmental impact in terms of CO2 emissions from computations. In this context, Recommender Systems (RS) are no exception, and the current literature in the field pays little attention to the concept of Green AI. In this paper, we propose a tool that aims at estimating the CO2 emitted by a recommendation model. Our contributions are twofold: first, we built a regression dataset that can be used to feed a regression model aiming at estimating the emissions or RS models; this dataset can be easily expanded, so it can be considered a relevant resource for the whole community. Second, we compared several state-of-the-art regression models to assess which performs the best and in which settings. Results show that Random Forest is the best performing model to effectively estimate the CO2 emissions produced by recommendation models