Applying Customer Loyalty Classification with RFM and Naïve Bayes for Better Decision Making

The problem faced by the e-commerce industry in determining customer loyalty is that it is very difficult to be classified into the form of promotions every year to customers who are feasible in terms of loyalty to the company. With the problems faced by the company based on the data, it is used for stakeholders' decision making. The differentiator in this study uses Naive Bayes as a classification method in detail to the attributes that are tested and the customer is classified by the RFM method and in previous studies that have been conducted by other researchers are still little discussing the combining of these two methods between Naive Bayes and RFM. Naive Bayes is a method of classifying data with the results of 62% feasible and not feasible 38% then assisted by RFM method as a data analysis to each customer based on segmentation use “usage rate” attribute on data so that with processed data can make a basic reference in making decisions.