Segmenting Customers with Data Mining Techniques

Abstract

Retail marketers are constantly looking for ways to improve the effectiveness of their campaigns. One way to do this is to target customers with the particular offers most likely to attract them back to the store and to spend more time and money on their next visit. Demographic market segmentation is an approach to segmenting markets. A company divides the larger market into groups based on several defined criteria. Age, gender, marital status, occupation, education and income are among the commonly considered demographics segmentation criteria. A sample case study has been done in order to explain the theory of segmentation applied on a Turkish supermarket chain. The purpose of this case study is to determine dependency on products and shopping habits. Furthermore forecast sales determine the promotions of products and customer profiles. Association rule mining was used as a method for identifying customers buying patterns and as a result customer profiles were determined. Besides association rules, interesting results were found about customer profiles, such as "What items do female customers buy?" or "What do consumers(married and 35-45 aged) prefer mostly?". For instance, female customers purchase feta cheese with a percentage of 60% whereas male customers purchase tomato with a percentage of 46%. Regarding to customers age, 65 and older customers purchase tea with a percentage of 58%, and customers aged between 1825 preferred pasta with a percentage of 57%.