customer segmentation using the extended rfmp model based on customer lifetime value (clv) and data mining

One important way for identifying customers is clustering them to congruent segments. skillfully clustering can be caused by identifying profitable customers by companies, understanding their requirement and allot their own resources in an appropriate way. we can also examine the change in the clustering of customers after the implementation of any economic policy and formulate and implement suitable public policies accordingly. the main goal of a recent study is clustering and identifying customers using of extended rfmp model. the study was done on 6665 customers of the zahedan refah chain store. according to this, after identification, the extended rfmp amounts (sum of recency, frequency, monetary and periodicity) weight of each variable was identified according to the analytic hierarchy process (ahp). at the next stage, optimal clusters number was specified by using silhouette and davies bouldin indexes and customers were clustered with the k-means algorithm and finally, customers were preferred according to customer lifetime value. according to results, customers were divided into 3 parts and their traits were analyzed. background can be provided for codifying relationship strategies with customers by using of recent study results.