A Case Study on Customer Segmentation by using Machine Learning Methods

Customer segmentation is important both in customer relationship management literature and softwares. The most common way to separate one customer from another is to promote a group of customers as premium and the remaining customers as standard. In this work, a company's manually segmented customer data is analyzed. The study aims to solve the company's data segmentation problem by using its real data regarding its customers' payments. Since, machine learning methods are useful to solve problems about data management, the solution is searched within machine learning methods. Different classification methods which are used to discriminate between premium and standard customers belonging to a company's database are compared. Two dimensional payment information of customers are used as input variables (features) and the methods are compared according to their separation performances.