F-EvoRecSys: An Extended Framework for Personalized Well-Being Recommendations Guided by Fuzzy Inference and Evolutionary Computing

People nowadays deal with busy and dynamic lifestyles on a daily basis. Adopting or maintaining a healthy lifestyle to prevent chronic conditions is therefore a core societal challenge. It is thus critical to engage and motivate citizens with healthy and tailored activities that they like , as a key driver for safeguarding good health from a preventive vantage point, aligned with the pursuance of SDG 3: “good health and well-being”. This is why Health Recommender Systems have recently become a research trend, particularly in the domains of food and physical activity recommendation. In this work, we present F-EvoRecSys: an extension of an evolutionary algorithm-driven solution for “healthy bundle” recommendations to help users improve their well-being. F-EvoRecSys presents the novelty of incorporating a fuzzy inference system with the aim of improving physical activity recommendations, predicated on users’ exercising habit information. Through an experimental study and a live study with real participants, we demonstrate the feasibility of F-EvoRecSys to produce more diversified recommendations, while maintaing a balance between adapting to the user health needs and matching her/his individual preferences. We finally provide a discussion about challenges and future directions for personalized well-being recommender systems, under three points of view: AI and data approaches, role of fuzzy systems, and application domain considerations.