Many-objective optimization meets recommendation systems: A food recommendation scenario

Due to the ever-increasing amount of various information provided by the internet, recommendation sys-tems are now used in a large number of fields as efficient tools to get rid of information overload. The content-based, collaborative-based and hybrid methods are the three classical recommendation tech-niques, whereas not all real-world problems (e.g. the food recommendation problem) can be best addressed by such classical recommendation techniques. This paper is devoted to solving the food recom-mendation problem based on many-objective optimization (MaOO). A novel recommendation approach is proposed by transforming the original recommendation problem into an MaOO one that contains four different objectives, i.e., the user preferences, nutritional values, dietary diversity, and user diet patterns. The experimental results demonstrate that the designed recommendation approach provides a more bal-anced way of recommending food than the classical recommendation methods that only consider indi-viduals' food preferences.Crown Copyright (c) 2022 Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).