{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/yum-me-a-personalized-nutrient-based-meal","title":"Yum-me: A Personalized Nutrient-based Meal Recommender System","arxiv_id":"1605.07722","date":"2016-05-25","proceeding":null,"authors":["Longqi Yang","Cheng-Kang Hsieh","Hongjian Yang","Nicola Dell","Serge Belongie","Curtis Cole","Deborah Estrin"],"abstract":"Nutrient-based meal recommendations have the potential to help individuals\nprevent or manage conditions such as diabetes and obesity. However, learning\npeople's food preferences and making recommendations that simultaneously appeal\nto their palate and satisfy nutritional expectations are challenging. Existing\napproaches either only learn high-level preferences or require a prolonged\nlearning period. We propose Yum-me, a personalized nutrient-based meal\nrecommender system designed to meet individuals' nutritional expectations,\ndietary restrictions, and fine-grained food preferences. Yum-me enables a\nsimple and accurate food preference profiling procedure via a visual quiz-based\nuser interface, and projects the learned profile into the domain of\nnutritionally appropriate food options to find ones that will appeal to the\nuser. We present the design and implementation of Yum-me, and further describe\nand evaluate two innovative contributions. The first contriution is an open\nsource state-of-the-art food image analysis model, named FoodDist. We\ndemonstrate FoodDist's superior performance through careful benchmarking and\ndiscuss its applicability across a wide array of dietary applications. The\nsecond contribution is a novel online learning framework that learns food\npreference from item-wise and pairwise image comparisons. We evaluate the\nframework in a field study of 227 anonymous users and demonstrate that it\noutperforms other baselines by a significant margin. We further conducted an\nend-to-end validation of the feasibility and effectiveness of Yum-me through a\n60-person user study, in which Yum-me improves the recommendation acceptance\nrate by 42.63%.","url_abs":"http://arxiv.org/abs/1605.07722v3","url_pdf":"http://arxiv.org/pdf/1605.07722v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"yum-me-a-personalized-nutrient-based-meal","repo_url":"https://github.com/ylongqi/FoodDist","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"yum-me-a-personalized-nutrient-based-meal","repo_url":"https://github.com/ali-nsua/quickRecommender","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}