Intelligent techniques have been used in the marketing and sales sectors of business to
improve analysis, increase revenues and save time. In customer-centric institutions, one of the areas in
which intelligent techniques and data mining algorithms have been used is the personalization for
enhanced CRM (customer relationship management) performance. However, with a growing number of
customers, the diversity of products on offer, the complex behavior of customer groups and the
continuous change of personalization parameters, the production of a tailored personalized
recommendation and the prediction of future needs are a challenging task. Within these institutions,
personalization that is more true to the customer needs leads to better targeted marketing campaigns
and enhances customer satisfaction with the ultimate aim of increasing the rates of customer retention,
and improving competitive advantage. Intelligent techniques and data mining algorithms have been
used to produce a more accurately tailored action or service to individual customers or segments of
customers. However, many limitations still exist in the CRM personalization lifecycle that undermine
the scope of personalized actions that follow; especially in evaluating of effectiveness of targeting,
ensuring the coverage of a large segment customers and the control on the decision making process.