Creative Flavor Pairing: Using RDC Metric to Generate and Assess Ingredients Combination

Creating culinary recipes is one of the most creative human activities. It requires combining ingredients, performing the recipe steps, creating specific diets, and others tasks. In addition to it, the existence of publicly available repositories of recipes, as well as scientific advances in areas such as Food Chemistry and Neuro-Gastronomy, encourage the generation of new and pleasurable recipes from algorithms. Although the number of ingredients allows the generation of a huge number of recipes (∼ 10), only a small fraction of this potential is exploited (∼ 10). This paper proposes, implements and analyzes a system called Creative Flavor Pairing which acts cooperatively with different profiles of cooks assuming the responsibility of suggesting food ingredients that can lead to creative recipes. These ingredient combinations are generated by a genetic algorithm using the RegentDependent Creativity (RDC) metric as a fitness function. Our experimental results showed that the RDC metric can be applied to the culinary field as our system was able to suggest creative ingredient combinations that match the most popular ones currently published in the largest cooking social net-