From Clicks to Carbon: The Environmental Toll of Recommender Systems

TL;DR

This paper assesses the environmental impact of recommender systems research by analyzing energy consumption and CO2 emissions of traditional versus deep learning algorithms in recent academic papers.

Contribution

It provides the first systematic comparison of the environmental footprint of recommender system algorithms over a decade of research.

Findings

Deep learning algorithms emit 42 times more CO2 than traditional methods.

A single deep learning paper generates over 3,000 kg of CO2 equivalents.

Recommender system research has a significant environmental impact.

Abstract

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.