NutRec: Nutrition Oriented Online Recipe Recommender

Abstract

In this paper we aim to solve a problem which many home-cooks encounter when searching for recipes online. Namely, finding recipes which best fit a handy set of ingredients while at the same time follow healthy eating guidelines. This task is especially difficult since the lion's share of online recipes have been shown to be unhealthy. In this paper we propose a novel algorithm which utilizes machine-learning techniques such as neural networks and matrix factorization in order to model the interactions between ingredients and their proportions within recipes for the purpose of offering suitable recommendations. The empirical results support the method's intuition and showcase its ability to retrieve healthier recipes.