Pendekatan Pemrograman Mixed-Integer pada Masalah Clustering dengan Aplikasi Segmentasi Pelanggan

Abstract

Segmentation is the process of dividing customers into clusters by customer loyal- ty categories to build a marketing strategy. Customer segmentation is one of the first steps in creating a business model. This research solves the cluster optimiza- tion problem with the combinatorial optimization approach chosen in producing the cluster optimization method. The combinatorial optimization in question is a combination of logic 0 and 1 in determining the optimal cluster, where 1 indi- cates an object that occupies an optimal cluster while 0 indicates an object that occupies a cluster that is not optimal. This means that the number of clusters designated with logic 1, produces the best optimization value. In this model to get the optimal number of clusters, the non-linear 0-1 problem model can guarantee that the smaller the distance between objects will be in the same cluster, that each object is only in one cluster, and that each cluster in k tests consists of at least one object.