Identification of Similarities and Clusters of Bread Baking Recipes Based on Data of Ingredients

We define the similarity of bakery recipes and identify groups of similar recipes using different clustering algorithms. Our analyses are based on the relative amounts of ingredients included in the recipes. We use different clustering algorithms to find the optimal clusters for all recipes, namely k-means, k-medoid, and hierarchical clustering. In addition to standard similarity measures we define a similarity measure using the logarithm of the original data to reduce the impact of raw materials that are used in large quantities. Clustering recipes based on their ingredients can improve the search for similar recipes and therefore help with the time-consuming process of developing new recipes. Using the k-medoid method, we can separate 1271 recipes into six different clusters. We visualize our results via dendrograms that represent the hierarchical separation of the recipes into individual groups and sub-groups.