Home  >  108 Data Analysis  > Data Analysis - Segments - RFM

RFM = Recency, Frequency, Monetary Value

RFM is a useful model to group a customer base into segments.

Every customer has their own pattern of transactions over time. Some transact all the time in every period, others purchase and then never come back. Recency and Frequency are the best indicators of whether a customer will transact again. (1) - Recency = How recently did the customer last transact? - Frequency = How many times did the customer transact in the measured periods? - Monetary Value = How much money has this customer spent in total?

RFM is a good tool for customer segmentation (as part of the 108.30.10 Data Analysis - Structural analysis)


RFM was originally developed in the direct marketing industry.


Segmentation with RFM is created by grouping different ranges of R and F+M. One way to do it:

Segment Recent Score Range Frequency + Monetary Score Range
Champions 4-5 4-5
Loyal Customers 2-5 3-5
Potential Loyalist 3-5 1-3
Recent Customers 4-5 0-1
Promising 3-4 0-1
Customers Needing Attention 2-3 2-3
About To Sleep 2-3 0-2
At Risk 0-2 2-5
Can’t Lose Them 0-1 4-5
Hibernating 1-2 1-2
Lost 0-2 0-2

When mapped in a grid it looks like this: !

Useful business problems to solve with RFM segmentation

Segmenting the customer base with RFM is a fabulous way to identify who/what to optimize. 108.20.10 Data Analysis - Optimize

Implementation Data Analysis - Segments - RFM - How to segment RFM

Variations of RFM model Data Analysis - Segments - RFM - variations

Other models that use RFM

Other prediction models use RFM data - 113.020.050 Statistics - BTYD models - BTYD - BGBB

Models that use RFM for prediction like BTYD - BGBB can be used to predict 108.20.30 Data Analysis - Customer lifetime value.

References: 1. https://www.putler.com/rfm-analysis/ 2. https://clevertap.com/blog/rfm-analysis/ 3. https://www.coursera.org/learn/wharton-customer-analytics/home - Week 3 slides, Fader