Clustering Orders

We propose a method of using clustering techniques to partition a set of orders. We define the term order as a sequence of objects that are sorted according to some property, such as size, preference, or price. These orders are useful for, say, carrying out a sensory survey. We propose a method called the ko’means method, which is a modified version of a k-means method, adjusted to handle orders. We compared our method with the traditional clustering methods, and analyzed its characteristics. We also applied our method to a questionnaire survey data on people’s preferences in types of sushi (a Japanese food).