Sent to this random sample of customers by email a purchase quote from the book The Art History of Florence, which recorded the intention to purchase from the list of potential consumers. Now, Stan knew the values of recent purchases, purchase frequency and the amount of each customer’s purchase. Stan aims to use the sending of test results to determine which groups of clients are more likely to respond. It shall address the offer customers email that if you have the option to purchase, thus reducing shipping costs. A secondary benefit is that customers with little interest in the book The Art History of Florence, will not receive the offer, but at the same time will not receive information that might not be interested by your buyer profile. Results Stan began by comparing those who bought The Art History of Florence with those who do not, in terms of the variables of recent purchases, purchase frequency and the amount of the purchase. Graphic 1 shows reports in the averages for the number of months since the last purchase (recent), the total number of purchases (frequency) and the invested money (purchase amount) total for the two groups of customers: those who bought The Art History of Florence and those that did not.

The results are consistent with what the RFM analysis could predict. Those who have responded to the offer were buyers more recent (8.6 months against the 12.7), the most frequent buyers (5.2 purchases compared with 3.8) and those who had more invested (US$ 234 against US$ 206). This suggests that the RFM model measurement variables are indicators of the response of customers to bid. Graphic 1 indicators of recent purchases, purchase frequency and purchase amount of buyers and no buyers in the next installment will discuss the steps to assess the response rate of each variable separately from the model RFM. This article has been developed based on the document called Recency, Frequency and Monetary (RFM) Analysis of Charlotte Mason of the University of Carolina of the North, United States.