14 Kg of CO2: Analyzing the Carbon Footprint and Performance of Session-Based Recommendation Algorithms
dc.catalogador | pva | |
dc.contributor.author | Plaza Carrasco, Alejandro | |
dc.contributor.author | Gil, Juan Carlos | |
dc.contributor.author | Parra Santander, Denis | |
dc.date.accessioned | 2025-04-28T16:39:13Z | |
dc.date.available | 2025-04-28T16:39:13Z | |
dc.date.issued | 2025 | |
dc.description.abstract | Green AI aims to develop accurate AI models that are also sustainable without compromising the environment, especially in terms of carbon emissions. There are few studies on this topic in recommender systems, so we analyzed the trade-offs between recommendation performance and carbon footprint in session-based recommender systems. We use five public e-commerce datasets to predict the next item a user will interact with based solely on their past click events. The GRU4Rec algorithm and five unofficial reimplementations in different deep learning frameworks (Theano, PyTorch, TensorFlow, Keras, and Reckpack) are evaluated. The results indicate a strong effect of the loss function and dataset size on the carbon footprint without significantly affecting the accuracy metrics. We show evidence that the implementation choice for the same algorithm strongly affects the CO2 emitted, and optimized implementations do not sacrifice recommendation efficiency, which should be considered when choosing a framework or implementation for an algorithm. | |
dc.format.extent | 12 páginas | |
dc.fuente.origen | ORCID | |
dc.identifier.doi | 10.1007/978-3-031-87654-7_12 | |
dc.identifier.eisbn | 978-3-031-87654-7 | |
dc.identifier.isbn | 978-3-031-87653-0 | |
dc.identifier.uri | https://doi.org/10.1007/978-3-031-87654-7_12 | |
dc.identifier.uri | https://repositorio.uc.cl/handle/11534/103484 | |
dc.information.autoruc | Escuela de Ingeniería; Plaza Carrasco, Alejandro; S/I; 1138899 | |
dc.information.autoruc | Escuela de Ingeniería; Gil, Juan Carlos; S/I; 1133691 | |
dc.information.autoruc | Escuela de Ingeniería; Parra Santander, Denis; 0000-0001-9878-8761; 1011554 | |
dc.language.iso | en | |
dc.nota.acceso | contenido parcial | |
dc.pagina.final | 134 | |
dc.pagina.inicio | 123 | |
dc.publisher | Springer, Cham | |
dc.relation.ispartof | Recommender Systems for Sustainability and Social Good: First International Workshop, RecSoGood 2024, Bari, Italy, October 18, 2024, Proceedings | |
dc.rights | acceso restringido | |
dc.subject | Information systems | |
dc.subject | Ecologic recommender systems | |
dc.subject.ddc | 000 | |
dc.subject.dewey | Ciencias de la computación | es_ES |
dc.subject.ods | 13 Climate action | |
dc.subject.odspa | 13 Acción por el clima | |
dc.title | 14 Kg of CO2: Analyzing the Carbon Footprint and Performance of Session-Based Recommendation Algorithms | |
dc.type | comunicación de congreso | |
sipa.codpersvinculados | 1138899 | |
sipa.codpersvinculados | 1133691 | |
sipa.codpersvinculados | 1011554 | |
sipa.trazabilidad | ORCID;2025-04-21 |