SUNConferences, 29th Annual Conference of SAIIE

Font Size: 
DEVELOPMENT AND DEMONSTRATION OF A CUSTOMER SUPER-PROFILING TOOL TO ENABLE EFFICIENT TARGETING IN MARKETING CAMPAIGNS
Marisa Walters, James Bekker

Last modified: 2018-10-09

Abstract


Being part of a competitive generation demands having good marketing policies to attract new customers as well as to retain existing customers. This research outlines a general methodology for segmentation of customers by using the model of Recency, Frequency and Monetary (RFM) to identify types of customers, and then predict their customer profiles, based on demographic and behavioural features. A few previous studies dealt with the question using non-aggregate customer data. We, however, also address the problem by using decision trees, something which has rarely been done before. We applied and demonstrated this tool on a large customer dataset and found useful results.


Full Text: PDF