Skip to content

RFM analysis

| Article: 2 min read | Customer retention

RFM analysis is a way to segment customers by three attributes: how recently they last bought (Recency), how often they buy (Frequency) and how much they spend (Monetary). It shows who to write to first and who has, it seems, already been lost.

In plain words

Wikipedia describes RFM as a method for assessing customer value and segmentation that is common in direct marketing. R is how long ago the customer bought, F is how often, M is how much they spend (Wikipedia)).

Its usefulness is that it needs no complex statistics: an order table with three columns is enough. According to the same article, proponents value its simplicity and the way its results are easy for a business to understand.

How to calculate it

There are two approaches (Wikipedia)):

  1. Scores from 1 to 10 on each axis, where the maximum is the desired behavior.
  2. Categories: for example, recency in three bins: up to 90 days, 91–365 days, over 365 days. Three categories across three attributes give 27 segments, five across three give 125, and small segments can be merged.

For a store with a small base, 3 × 3 × 3 or even simpler groups are enough.

Example (hypothetical numbers)

The numbers are made up for the example. A cosmetics store. Customer Olena: last purchase 20 days ago (R is high), 4 orders in a year (F is high), 5,000 UAH in a year (M is high). Customer Andriy: one order 14 months ago for 600 UAH (all three are low).

Segment

What to do

Longtime, frequent, big spenders

A reminder and a personal offer

New, one order

A series of emails aimed at a second purchase

Longtime, one order

One or two attempts to win back, then stop spending budget

Limitations

Wikipedia warns that the most valuable segments may be a fluke of the data, and advises checking the results on a separate data set (Wikipedia)). So don't build a strategy on a segment of 15 people.

Common mistakes

  • Seeing only M, that is, big amounts, and forgetting about recency.
  • Too many segments for a small base.
  • Not updating: RFM should be recalculated every month.
  • Not subtracting returns and unclaimed orders.

FAQ

What is RFM analysis in plain words? Splitting customers by how recently, how often and for how much they bought.

What do R, F and M stand for? Recency, Frequency, Monetary: how recent, how frequent, how much money.

What is RFM for in an online store? For campaigns and offers to different groups: active, dormant, new. It helps raise retention.

How many segments do you need? A few are enough. Large numbers (27, 125) exist, but small segments are usually merged.

Sources

Share

Related

  • Customer surveys

    | Article: 2 min read

    Customer surveys are short questions to customers about their experience (why they bought, what they couldn't find, how delivery went) that give a store what numbers don't show: reasons. Analytics shows where people stop, a survey helps you understand why.

  • Customer churn

    | Article: 2 min read

    Customer churn rate is the share of customers who left a group over a given period. The opposite measure is retention.

  • Customer service and replies to shoppers

    | Article: 2 min read

    An online store's customer service is everything that happens between a shopper's question and its resolution: answers before purchase, order status, changes, returns, complaints. It is part of the product: a shopper judges a store by how their issue was…

  • NPS and CSAT

    | Article: 3 min read

    NPS (Net Promoter Score) is a loyalty index: buyers are asked how likely they are to recommend the store on a scale from 0 to 10, and the share of critics is subtracted from the share of promoters. CSAT (Customer Satisfaction Score) is a rating of…