RFM segmentation

RFM segmentation scores each customer on three behaviours: how recently they bought, how often they buy, and how much they spend. Teams use it to decide who gets a reactivation message, who gets a rewards push and who should be left alone, without building a predictive model first. Scores are normally assigned by quintile within your own base, so they are relative — an RFM 5 at one retailer would be an RFM 2 at another. Recency does most of the predictive work.