Recently, as the population of customers is becoming global, the growing competitive pressure has forced the marketing industry to use different strategies in order to create valuable customers and serve them profitably. Through scrutinizing customers’ purchasing behavior, marketers will be able to identify their potential group of customers. Marketing such potential customers directly will minimize cost by avoiding unwanted promotions and improve the response rate especially when mailing the product to customers who would be most capable, enthusiastic and want to buy. Artificial neural networks (ANNs) have been used in many business applications in problems such as classification, pattern recognition, forecasting, optimization and clustering. This paper aims to use self organizing map SOM (an artificial neural networks model) to segment customers according to their purchasing behavior. The results showed that SOM is one of best practices that can be used in customer segmentation.