Food Recommendations for Reducing Water Footprint

Abstract

Most existing food-related research efforts focus on recipe retrieval, user preference-based food recommendation, kitchen assistance, or nutritional and caloric estimation of dishes, ignoring personalized and conscious food recommendations resources of the planet. Therefore, in this work, we present a personalized food recommendation scheme, mapping the ingredients to the most resource-friendly dishes on the planet and in particular, selecting recipes that contain ingredients that consume as little water as possible for their production. The system proposed here is able to understand the user’s behavior and to suggest tailor-made recipes with lower water quantity used in production. By continuously using the system, the user can gradually reduce their water footprint and benefit from a healthier diet. The proposed recommendation system was compared with the results of two papers available in the literature that represent the state of the art, obtaining similar results. Therefore, the results of the presented recommendation system can be considered reliable.