# From Clicks to Carbon: The Environmental Toll of Recommender Systems

arXiv: https://arxiv.org/abs/2408.08203 · HTML: https://mlsanity.com/paper/2408.08203/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Aug 2024.

## Built on by (most cited first, 11 of 11)

- [Do LLMs Memorize Recommendation Datasets? A Preliminary Study on MovieLens-1M](https://mlsanity.com/paper/2505.10212/) (2025)
- [What do Large Language Models Say About Animals? Investigating Risks of Animal Harm in Generated Text](https://mlsanity.com/paper/2503.04804/) (2025)
- [Green Recommender Systems: Optimizing Dataset Size for Energy-Efficient Algorithm Performance](https://mlsanity.com/paper/2410.09359/) (2024)
- [Recommender Systems for Good (RS4Good): Survey of Use Cases and a Call to Action for Research that Matters](https://mlsanity.com/paper/2411.16645/) (2024)
- [e-Fold Cross-Validation for Recommender-System Evaluation](https://mlsanity.com/paper/2412.01011/) (2024)
- [One Search Fits All: Pareto-Optimal Eco-Friendly Model Selection](https://mlsanity.com/paper/2505.01468/) (2025)
- [We're Still Doing It (All) Wrong: Recommender Systems, Fifteen Years Later](https://mlsanity.com/paper/2509.09414/) (2025)
- [From Theory to Practice: Implementing and Evaluating e-Fold Cross-Validation](https://mlsanity.com/paper/2410.09463/) (2024)
- [Involution-Infused DenseNet with Two-Step Compression for Resource-Efficient Plant Disease Classification](https://mlsanity.com/paper/2506.00735/) (2025)
- [The Unreasonable Effectiveness of Data for Recommender Systems](https://mlsanity.com/paper/2604.06420/) (2026)
- [Ensembles at Any Cost? Accuracy-Energy Trade-offs in Recommender Systems](https://mlsanity.com/paper/2604.07869/) (2026)

## Abstract (arXiv)

As global warming soars, the need to assess the environmental impact of research is becoming increasingly urgent. Despite this, few recommender systems research papers address their environmental impact. In this study, we estimate the environmental impact of recommender systems research by reproducing typical experimental pipelines. Our analysis spans 79 full papers from the 2013 and 2023 ACM RecSys conferences, comparing traditional "good old-fashioned AI" algorithms with modern deep learning algorithms. We designed and reproduced representative experimental pipelines for both years, measuring energy consumption with a hardware energy meter and converting it to CO2 equivalents. Our results show that papers using deep learning algorithms emit approximately 42 times more CO2 equivalents than papers using traditional methods. On average, a single deep learning-based paper generates 3,297 kilograms of CO2 equivalents - more than the carbon emissions of one person flying from New York City to Melbourne or the amount of CO2 one tree sequesters over 300 years.