thankQ Help

The purpose of RFM scoring is to project future behaviour (driving better segmentation decisions).

In order to allow projection, it is important to translate the customer behaviour into numbers which can be used through time.

Too often, direct marketers will use static customer selections. When initially building their segmentation system, they may consider their best customers to be those who have purchased more than, say, $100. If the mailer is relatively new, this definition will degrade rapidly. The initial selection of >$100 may have encompassed 20% of the customer file.

After a year or two, it may easily identify the top 30%-40%. If we evaluate the profitability of our first contact based on the $100 cut off, we will see very positive results. Given the successful segmentation experiment, the direct marketer will again use the $100 cut off. After substantial time elapses, that same $100 will yield poorer results. It is not that the best customers have significantly changed it is simply that over time, more customers will have repeat purchases and achieve the $100 threshold.

Two common scoring methods are used to avoid the bracket creep problem.