Data-driven recipe completion using machine learning methods

• 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.

BackgroundCompleting 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 approachIn 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 conclusionsThe 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.