Intelligent menu planning: recommending set of recipes by ingredients

With the growth of recipe sharing services, online cooking recipes associated with ingredients and cooking procedures are available. Many recipe sharing sites have devoted to the development of recipe recommendation mechanism. However, there is a need for users to plan menu of meals by ingredients. While most research on food related research has been on recipe recommendation and retrieval, little research has been done on menu planning. In this paper, we investigate an intelligent menu planning mechanism which recommending sets of recipes by user-specified ingredients. Those recipes which are well-accompanied and contain the query ingredients are returned. We propose a graph-based algorithm for menu planning. The proposed approach constructs a recipe graph to capture the co-occurrence relationships between recipes from collection of menus. A menu is generated by approximate Steiner Tree Algorithm on the constructed recipe graph. Evaluation of menu collections from Food.com shows that the proposed approach achieves encouraging results.