An open-source nutrient-based food recommendation service described in the following publication:
Longqi Yang, Cheng-Kang Hsieh, Hongjian Yang, JP Pollak, Nicola Dell, Serge Belongie, Curtis Cole, Deborah Estrin, "Yum-me: A Personalized Nutrient-based Meal Recommender System" ACM Transactions on Information Systems (TOIS), 36.1 (2017): 7.
This repo contains backend and frontend implementations of the end-to-end user study.
The service is built on Flask. Recipe metadata and pretrained models can be downloaded via the following link:
https://drive.google.com/drive/folders/1ZxEF4I6MYlQlRIG7ihwH-Hr2Ac9CTNGS?usp=sharing
For FoodDist model, please refer to: https://github.com/ylongqi/fooddist
Contact: Longqi Yang, ylongqi@cs.cornell.edu