Recipe recommendation: accuracy and reasoning

Abstract. Food and diet are complex domains for recommender tech-nology but the need for systems which assist users in embarking on and engaging with healthy living programs has never been more real. With the obesity epidemic reaching new levels each day many practitioners are looking to ICT for novel and effective ways to engage and sustain engage-ment with online solutions. Here we report on a large scale analysis of real user ratings on a large set of recipes in order to judge the applicability and practicality of each. We use traditional content based, collaborative filtering and machine learning algorithms and discuss the trends in the data which reflect user reasoning and decision making strategies