Recency Frequency Monetary (RFM) Customer Segmentation

RFM Analysis. It is a marketing technique used to quantitatively determine which customers are the best ones by examining their shopping behaviour – how recently a customer has purchased (recency), how often they purchase (frequency), and how much the customer spends (monetary). RFM analysis is based on an extension of Pareto’s principle which says that “80% of your business comes from 20% of your customers.

Customers who have purchased more recently, more frequently, and have spent more money, are likelier to buy again. But those who haven’t, are less valuable for the company and therefore, likely to churn. RFM stands for:

  • Recency – How recently did the customer purchase?

Recency is the most important predictor of who is more likely to show loyalty towards your brand. Customers who have purchased recently from you are more likely to purchase again from you compared to those who did not purchase recently.

  • Frequency – How often do they purchase?

The second most important factor is how frequently these customers purchase from you. The higher the frequency, the higher is the chances of such customers making a repeat purchase.

  • Monetary – How much money do they spend (average basket value)?

The third factor is the amount of money spent by these customers on their purchases. Customers who have spent higher are more likely to buy again compared to those who haven’t. By giving points for various hierarchies, you can easily find out who your best customers are.

How does it work?

To perform RFM analysis for your customers, each customer is assigned a score for their recency, frequency, and monetary value, and then a final RFM score is calculated.

Recency score is determined according to the date of their most recent purchase with your store. The scores are attributed based on the values of each parameter. Betaout’s RFM Analysis follows a category system of 0 to 9, score of 9 being the highest. In this case, customers who purchased within the last one month have a recency score of 9, customers who purchased within the last 1-2 months have a score of 8 and so on.

Similarly, the frequency score is calculated based on the number of times the customer has purchased in a given period of time. Customers with higher frequency receive a higher score.

Finally, customers are assigned a score based on the amount of money that they spent on their purchases. For calculating this score, you may consider the actual amount spent or the average spent per visit.

By combining these three scores, a final RFM score is calculated. The customers with the highest RFM score are considered to be the ones that are most likely to respond to your communication. In Betaout’s RFM Analysis, the RFM score range from 0 to 27. Customers with a score of 27 are your best customers.

Once you’ve calculated the RFM scores, you can create segments of customers based on their RFM scores to easily identify their relationship with your brand. Betaout uses the following framework to sort customers based on their RFM score:

There are 6 main types of segmentation:

  1. Profile Demographics – Start with the basics, such as age, gender and geography
  2. Customer Value – The idea here is to establish an understanding of who your most valued customers are. This way you can create a loyalty group and create a VIP mailing list to your highest valued segment
  3. Lifecycle groups: This refers to where your customer traveling through the online loyalty ladder. This is where the lifecycle segmentation approach is applied in order to encourage the visitors/customers along the ladder to further development.
  4. Purchase behavior: By collecting the data of how a customer interacts with your site or mobile app, you will then be able to create a detailed understanding of their current as well as predicted behavior. You will also be able to send them individualized content and offers in response to their actions
  5. Multi-channel preference: Every customer is different and every customer has a channel preference or multiple preferences for different purposes. These preferences can vary depending on the time of day, type of communications etc
  6. Personas: A marketing persona is a great technique that can help you develop a more engaging relationship with your customers. A marketing persona is a summary of your customers’ characteristics, needs, motivations, and the environment. This persona is a fictional model of a person that depicts the key characteristics of a group of users. It enables a company to provide the best user experience for its customers across the board

Image result for customer segmentation cluster analysis platinum gold silver

  • Split the values into buckets. Using quantiles or percentiles are a commonly used method for this but you can search online for more advanced methods.

Add segment numbers to the customer table that we had in the first step.

You can use a stacked contingency table to count/identify customers at risk or suitable for promotions/cross selling.


Comments & Responses

Leave a Reply

Your email address will not be published. Required fields are marked *