Data Mining Based CustomerResponse Prediction for a Specific Campaign in Pent

Abstract

PENTİ was established in 1950 in Turkey. Il is growing in produc­tion and retail activities, expanding its offering of mainly women’s and girls' socks, home wear and beachwear. Different campaigns are or­ganized to increase sales and customers are informed about the cam­paigns mostly by SMS regardless of their previous purchasing behav­ior. However, there is not an analytical tool to determine which cus­tomers those SMS should be sent to in order to get a high number of responses. In this study, an analytical tool which will predict the possible re­sponses of customers to a specific campaign will be developed by using WEKA software. While developing this tool, attributes such as age, having child, marital status and city information of customers will be preprocessed to analyze which ones are distinguishing when determin­ing the final attribute which is the response of customers. Following that, several data classification algorithms will be applied and the one which has the best accuracy rate will be proposed to the company. By the help of this tool. SMSs can be sent to the customers considering those attributes and the company can reach right group of people who will do shopping at stores after those informative SMSs.