Data-driven recipe completion using machine learning methods. (March 2016)

• Record Type: Journal Article
• Authors: De Clercq, Marlies; Stock, Michiel; De Baets, Bernard; Waegeman, Willem
• Is Part Of: Trends in food science & technology. Volume 49(2016)
• Page Start: 1
• Page End: 13
• Publication Date: 2016-03
• Subjects: Ingredient combinations -- Recipe completion -- Non-negative matrix factorization -- Two-step regularized least squares -- Recommender systems; Food industry and trade -- Periodicals; Food -- Biotechnology -- Periodicals; 664.005
• DOI: 10.1016/j.tifs.2015.11.010
• Languages: English
• ISSNs: 0924-2244

Abstract

Abstract: Background: Completing recipes is a non-trivial task, as the success of ingredient combinations depends on a multitude of factors such as taste, smell and texture. Scope and approach: In this article, we illustrate that machine learning methods can be applied for this purpose. Non-negative matrix factorization and two-step regularized least squares are presented as two alternative methods and their ability to build models to complete recipes is evaluated. The former method exploits information captured in existing recipes to complete a recipe, while the latter one is able to also incorporate information on flavor profiles of ingredients. The performance of the resulting models is evaluated on real-life data. Key findings and conclusions: The two machine learning methods can be used to build models to complete a recipe. Both models are able to retrieve an eliminated ingredient from a recipe and the two-step RLS model is also capable of completing an ingredient set to create a complete recipe. By applying machine learning methods on existing recipes, it is not necessary to model the complexity of good ingredient combinations to be able to complete a recipe. Highlights: Recipe completion can be performed using machine learning methods. The resulting models determine possible ingredient combinations. Non-negative matrix factorization can retrieve an eliminated ingredient from a recipe. Two-step regularized least squares can complete an ingredient set to form a recipe. Cuisine and type of dish are main factors in ingredient selection.