Towards Recommendations for Value Sensitive Sustainable Consumption (Papers Track)

Thomas Asikis (University of Zurich)

Paper PDF Slides PDF Poster File Recorded Talk NeurIPS 2023 Poster Cite
Recommender Systems Societal Adaptation & Resilience


Excessive consumption can strain natural resources, harm the environment, and widen societal gaps. While adopting a more sustainable lifestyle means making significant changes and potentially compromising personal desires, balancing sustainability with personal values poses a complex challenge. This article delves into designing recommender systems using neural networks and genetic algorithms, aiming to assist consumers in shopping sustainably without disregarding their individual preferences. We approach the search for good recommendations as a problem involving multiple objectives, representing diverse sustainability goals and personal values. While using a synthetic historical dataset based on real-world sources, our evaluations reveal substantial environmental benefits without demanding drastic personal sacrifices, even if consumers accept only a fraction of the recommendations.

Recorded Talk (direct link)