Customer Segmentation: Using a Comparative Case of Clustering Algorithms

Customer analysis is done by all businesses in some way or the other. It is the process of understanding who our customers are, their location and what make them to buy our products and services. Recent developments in the fields of business investment, scientific research and information technology have resulted in the collection of massive data which becomes highly useful in finding certain patterns governing the data source. Customer segmentation is a way to have more targeted communication with the customers. The process of segmentation describes the characteristics of the customer groups within the data. Clustering algorithms are popular in finding hidden patterns and information from such repository of data. This paper presents how different clustering algorithms can be compared and the optimal one can be selected for the purpose of customer segmentation for a shop. The information extracted can be used to satisfy the needs of the key customers and also helps in making strategic decision as to how the business can be expanded. This paper compares the four clustering algorithms: K-means, K-medoid, Fuzzy C-means and Gustafson-kessel. The best one is selected and optimal number of clusters is found out and applied to that algorithm for customer segmentation.