Comparing data reduction strategies for energy-efficient green recommender systems

As recommendation algorithms become increasingly sophisticated and pervasive, their energy consumption and associated carbon emissions are rising significantly. To address this growing environmental concern, this work investigates the path toward ‘green recommender systems’ by examining how data reduction techniques can impact on algorithm performance and carbon footprint. We specifically investigated whether and how a reduction of the training data impacts the performance of several representative recommendation algorithms. To obtain a fair comparison, all the algorithms were run based on the implementations available in a popular recommendation library, i.e., RecBole, and by using the same experimental settings. Specifically, we employed distinct data reduction strategies: (a) random sampling of either users or item ratings; (b) reducing the overall dataset size; (c) filtering out more recent user ratings. Results indicate that data reduction can be a promising strategy to make recommender systems more environmentally sustainable with a relevant reduction in carbon emissions at the cost of a smaller reduction in predictive accuracy -43.38% of emissions for LightGCN algorithm and only 3.72% loss in accuracy in a book recommendation scenario). Moreover, training recommender systems with less data makes the suggestions less prone to popularity bias. Overall, this study contributes to the ongoing challenge of developing recommendation algorithms that meet the principles of Sustainable Development Goals, by proposing the adoption of more sustainable practices in the field.