blog-symplify.png

© 2000-2019 Symplify

All rights reserved.

Privacy Policy | Anti-Spam Policy

FEATURES

RFM Analysis

What is it and what can I use it for?

RFM stands for Recency, Frequency, Monetary. This technique has been around for over 50 years and could even be considered the grand-father of data mining. The most widely used method was developed by Arthur Middleton Hughes. This method splits your entire user database into 125 cells organized into a tabular format with Frequency and Recency axis.

The concept is to rate Recency, Frequency, Monetary on a scale of 5. So a user that will have a Recency of 5, Frequency of 3, Monetary of 2 will fit into the “Potential Loyalists” category.

When processed, all your users will fit into this graph as a “dot”, where the dot lands determine their RFM category. All the 1 to 5 ratings are calculated by using your own purchase data. So if you’re making sales once a year on average, people that buy from you once a year will be a 5 but people that buy once every 2 years might get a lower rating. Compared to higher-volume markets where it takes meer months to go from 5 to 1.

Why should you care?

RFM techniques have been around for a long time and in some cases can drive over 75% of all your segmentation needs. Using this method can create some very powerful automated flows if using the correct platform. Your customer’s habits will change over time and will move from group to group. Using a powerful automation tools will allow you to build flows that will help guide those changes in your favor.

 

EX1: Car vendors typically have a longer sales cycle and will put more emphasis on returning customers. This will translate into “brand loyalty” so you can safely assume that their new vehicle will be the same brand.

  • Focus might be on At-Risk category: 

    • Spent big money and purchased often a long time ago.

Note here that I’m focusing on a group that I consider “purchased often” that is the beauty of RFM since you’re selling high priced low volume item on low sale cycles, “often” for your industry is maybe once every 5 years compared to lower-priced high volume items.

EX2: On the other extreme, you might have a subscription model and might want to make sure customers that are about to end their first year resubscribe because market research shows over 60% of first-year subscribers if renewed will go for the third year.

  • Focus might be on Needing Attention category: 

    • Above-average recency, frequency, and monetary values, but they may not have bought very recently though.

This will target customers that are fairly recent (first-year subscription) and spent a decent amount (1year subscription) but did not spend recently (did not renew for second year)

 

There’s no right or wrong answers here, it all depends on your objectives, RFM analysis is a valuable tool to help you make the best decisions.

What do I need to use RFM analysis?

This method can be applied to all data sets containing Purchase History, an incremental record of every transaction your user makes.

 

The record will require at least:

  1. Item SKU / ID

  2. Item Quantity

  3. Transaction Date

  4. Transaction Value / Price

 

You could also track additional information like:

  • Item Actual Cost (Able to calculate profits)

  • Item Category (Split data by Category)

  • Item Color (Additional insights into your products)

 

This information may change wildly depending on your industry. The more data the more insights you will gain.

Meet the 11 RFM Groups

Champions

Bought recently, and often they spend the most!

Loyal Customer

Spend good money with us often.

Potential Loyalist

Recent customers, but spent a good amount and bought more than once.

Recent Customers
Bought most recently, but not often.

Promising
Recent shoppers, but haven’t spent much.

Customers Needing Attention
Above-average recency, frequency, and monetary values, but they may not have bought very recently though.

About To Sleep
Below average recency, frequency, and monetary values. Will lose them if not reactivated.

At-Risk
Spent big money and purchased often a long time ago. You need to bring them back!

Can’t Lose Them
Made biggest purchases and often but haven’t returned for a long time.

Hibernating
The last purchase was long back, low spenders and a low number of orders.

Lost
Lowest recency, frequency, and monetary scores.