WSEAS Transactions on Business and Economics
Print ISSN: 1109-9526, E-ISSN: 2224-2899
Volume 12, 2015
Customer Segmentation Using Data Warehouse and Neural Networks
Authors: Dajana Ćorić, Katarina Ćurko, Zvonko Merkaš
Abstract: The success of a company depends on its effective customer management. An intelligent company can achieve this goal by using modern information technology. This paper shows how data warehouse and neural networks can be useful in the process of predicting customer segments. The aim of this paper is to determine how neural networks, as a data mining method, are able to predict the belonging of each customer to a specific segment based on data from data warehouse. This paper presents a research on analysing data set of customers of the company which take care of production and distribution of nuts, grains and dried fruit. As a result there will be three groups of customers: a group containing the most profitable customers, a group of customers with a profit close to zero, and a group of the least profitable customers. Depending on where a specific customer belongs, a company will use different marketing activities in order to retain them, move them to a more profitable segment or ultimately reject them. The customer activity in the first quarter will be used to predict a segment in which a customer belongs at the end of the year. This will show the predictive ability of neural networks and how reliable they are in the process of customer segmentation using data from data warehouse.
Keywords: customer, profitability, data warehouse, data mining, neural networks
Pages: 186-197WSEAS Transactions on Business and Economics, ISSN / E-ISSN: 1109-9526 / 2224-2899, Volume 12, 2015, Art. #17