Machine Learning (ML) became the predominate research paradigm in Recommender Systems over the last several years leading to many fundamental advances in the field, both in the academia and in the industry. Unfortunately, these achievements were accomplished as a result of shifting focus from other research paradigms towards ML. In this talk, I will argue that it is crucial for the Recommender Systems field to broaden its scope of inquiry by enhancing its focus on other disciplines, such as psychology and marketing, sociology and social science, management and organizational behavior, economics, decision science and other disciplines that have been underexplored in Recommender Systems. By shifting the focus of inquiry towards the “exploration” component of the explore-exploit paradigm, we can potentially achieve new significant breakthroughs in recommender Beyond Algorithms: Reclaiming the Interdisciplinary Roots of Recommender Systems Workshop (BEYOND 2025), September 26th, 2025, co-located with the 19th ACM Recommender Systems Conference, Prague, Czech Republic.
systems. I will present some case studies supporting this claim. CEUR