Cluster Analysis: Application of K-Means and Agglomerative Clustering for Customer Segmentation

Abstract

Customer segmentation is the division of a business customersinto categories called customer segments such that each customer segment exhibits similar characteristics. This division of customers is built on factors that can directly or indirectly affect the market or business such as product preferences or expectations, locations, behaviours etc. Customer segmentation can be implemented through clustering, which is one of the highlyrecognized machine learning techniques. Cluster analysis is applied in many business applications, from customized marketing to industry analysis. It is an unsupervised learning technique that divides a dataset into a set of meaningful sub-classes, called clusters. It helps to comprehend the natural grouping in a dataset andcreate clusters of similar records which depends on several measurements made in the form of attributes.

This research paper has focused on creating customers clusters by applying K-means and Agglomerative clustering algorithms on a dataset consisting of 200 customers. Various machine learning libraries were used in Python programming language to implement and visualize the results.