Recommender Systems for Sustainability: Overview and Research Issues

TL;DR

The paper surveys how recommender systems can support all 17 UN SDGs by mapping macro-level organizational and micro-level individual applications to sustainability goals. It synthesizes state-of-the-art approaches across CF, CBF, KBR, HYB, and GRP, emphasizing scenario-driven usage and explanations rather than deep algorithmic specifics. Key contributions include a structured SDG-by-SDG overview with concrete examples, and a discussion of open research issues such as sustainability-oriented evaluation metrics, nudging, and explainable constraint-based decision support. The work highlights potential real-world impact in areas like poverty alleviation, sustainable energy, urban planning, and responsible consumption, while outlining research directions to make recommender systems more trustworthy, fair, and effective for sustainability outcomes.

Abstract

Sustainability development goals (SDGs) are regarded as a universal call to action with the overall objectives of planet protection, ending of poverty, and ensuring peace and prosperity for all people. In order to achieve these objectives, different AI technologies play a major role. Specifically, recommender systems can provide support for organizations and individuals to achieve the defined goals. Recommender systems integrate AI technologies such as machine learning, explainable AI (XAI), case-based reasoning, and constraint solving in order to find and explain user-relevant alternatives from a potentially large set of options. In this article, we summarize the state of the art in applying recommender systems to support the achievement of sustainability development goals. In this context, we discuss open issues for future research.