Green Recommender Systems: Understanding and Minimizing the Carbon Footprint of AI-Powered Personalization

2025-09-16

AI Summary

The environmental impact of recommender systems—particularly AI-driven personalized recommenders—remains poorly quantified despite their growing computational demands. Method: We conduct the first systematic carbon footprint assessment of 79 representative papers published at ACM RecSys over the past decade, using hardware-level energy measurements and CO₂-equivalent conversion models to quantify emissions across their computational workflows. Contribution/Results: We find that deep learning–based recommendation models emit, on average, 2,909 kg CO₂e per paper—42× higher than traditional models and equivalent to the per-passenger emissions of a New York–Melbourne flight. Emissions strongly correlate with model complexity and training scale. Based on these findings, we propose design principles for energy-efficient, green recommender systems. This work establishes a critical empirical benchmark and actionable technical pathway for sustainable AI in recommendation, advancing green AI research and practice in this domain.

Technology Category

• Data Mining & Knowledge Management: Recommender Systems
• Machine Learning: Efficient ML / Green AI
• Humans and AI: Other Foundations of Human Computation & AI

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Systems and Infrastructure for Web, Mobile and WoT: Sustainability and carbon-aware systems for Web, mobile, and WoT
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

As global warming soars, the need to assess and reduce the environmental impact of recommender systems is becoming increasingly urgent. Despite this, the recommender systems community hardly understands, addresses, and evaluates the environmental impact of their work. In this study, we examine the environmental impact of recommender systems research by reproducing typical experimental pipelines. Based on our results, we provide guidelines for researchers and practitioners on how to minimize the environmental footprint of their work and implement green recommender systems - recommender systems designed to minimize their energy consumption and carbon footprint. Our analysis covers 79 papers from the 2013 and 2023 ACM RecSys conferences, comparing traditional "good old-fashioned AI" models with modern deep learning models. We designed and reproduced representative experimental pipelines for both years, measuring energy consumption using a hardware energy meter and converting it into CO2 equivalents. Our results show that papers utilizing deep learning models emit approximately 42 times more CO2 equivalents than papers using traditional models. On average, a single deep learning-based paper generates 2,909 kilograms of CO2 equivalents - more than the carbon emissions of a person flying from New York City to Melbourne or the amount of CO2 sequestered by one tree over 260 years. This work underscores the urgent need for the recommender systems and wider machine learning communities to adopt green AI principles, balancing algorithmic advancements and environmental responsibility to build a sustainable future with AI-powered personalization.

Problem

• Assessing environmental impact of AI recommender systems
• Comparing carbon footprint between traditional and deep learning models
• Providing guidelines for implementing green recommender systems

Innovation

• Reproduce experimental pipelines to measure energy consumption
• Compare traditional and deep learning models' CO2 emissions
• Provide guidelines for minimizing recommender systems' carbon footprint