I started toying with RFM in the mid-80’s. The IBM PC entered the world and I learned how to use Visicalc and Lotus 1,2,3. With widespread computing came the possibility of the marketing dept. getting one. I remember stopping in Yankton, SD at the Gurnee Seed & Nursery Catalog. They weren’t doing any segmentation, keeping their picking slips in boxes, they didn’t even know which customers had bought more than once. I gave them some suggestions on getting those computerized and explained RFM.
So RFM is pretty ancient, but amazingly retailers and dot coms (like Gurnee) are just now finding out about it. This week, for a presentation on RFM, I searched and found more than a dozen new RFM articles within just this past 30 days.
Why is RFM so powerful and does it still matter in an age of Machine Learning and AI? I contend it does… and this website is dedicated to exploring that questions. I accidentally erased a 20-year old version of this site, so I’m rebuilding it, up to date with 2023. Stay tuned to get the latest information. – John
It’s the concept of taking action with a stream of marketing activities designed to capitalize on a positive customer action.
Here’s some actual data. The table in this post is for one-time buyers. The rows represent months since last purchase, the two columns show the probability of a customer purchasing in the next month given recency status and whether the customer visited the website in the past month. Take a look at the table.
Some of you have classic direct marketing training, and you are very familiar with RFM (recency / frequency / monetary) segmentation. You know that a customer who bought two months ago is a great customer, regardless of purchase frequency.
However … look at the table.
A customer who purchased two months ago and did not visit the website last month had a 3.7% chance of buying again in the next month. Now look at a customer with recency of 13-15 months ago, but the customer did visit the website in the past month. This customer has a 7.3% chance of buying again next month. With identical purchase frequency, the 13-15 month buyer (with a website visit in the past month) is 2x as likely to buy as a customer with recency = 2 months and no website visit in the past month.
I’ve been hard on the concept of “engagement” in my career – mostly because mutton-headed marketers will do anything to pursue engagement at the expense of protecting a healthy customer base.
But here’s a really good example of keeping a customer interested between purchases. If you do that, and do it the right way, your customer is much more likely to purchase.
This is where Action Streams come into play. If you are an email marketer, work with your email service provider to take action when a customer visits your website. Execute “streams” that encourage the customer to purchase. If you love offering discounts, here’s where you do it. If you know what the customer looked at, email the customer with similar merchandise. Set up a stream with five unique emails tailored to this individual customer … discounts (if that is your thing), content, new items from the same merchandise category, similar items to what the customer looked at previously, similar items to what the customer purchased previously.
The key is an Action Stream that is different (personalized) from the batch-and-blast email campaigns you’d normally send. You already send cart abandonment emails … this is extending the cart abandonment concept to a different level.
Does the concept of Action Streams make sense? The data suggests it is more than worth doing … anybody who visited your website in the past month is more responsive in the next month than many of your recent customers.
RFM analysis is a technique used in marketing and customer analytics to segment customers based on their past purchasing behavior. RFM stands for Recency, Frequency, and Monetary value, which are three key metrics used to evaluate customer engagement and profitability. Here’s how RFM analysis works and its use in marketing:
1. Recency (R): Recency refers to the time since a customer’s last purchase. Customers who have made recent purchases are generally considered more engaged and likely to make additional purchases.
2. Frequency (F): Frequency measures how often a customer makes purchases within a specific timeframe. Customers who make frequent purchases demonstrate higher loyalty and engagement with the brand.
3. Monetary Value (M): Monetary value represents the amount of money a customer has spent on purchases. High-value customers contribute more to the revenue and profitability of a business.
By analyzing these three metrics, RFM analysis helps classify customers into distinct segments, allowing marketers to tailor their marketing strategies and initiatives. Here are some common use cases of RFM analysis in marketing and customer analytics:
1. Customer Segmentation: RFM analysis allows marketers to segment their customer base into different groups based on their RFM scores. For example, “Champions” may represent customers with high scores in all three categories, indicating they are highly engaged, loyal, and valuable. Other segments may include “At Risk” customers who haven’t made a purchase in a long time, “New Customers” who recently made their first purchase.
2. Targeted Marketing Campaigns: Once customers are segmented based on RFM analysis, marketers can create targeted marketing campaigns tailored to each segment. For example, they can design reactivation campaigns to re-engage “At Risk” customers, loyalty programs to reward and retain “Champions,” or personalized offers to upsell or cross-sell to specific segments.
3. Customer Lifetime Value (CLV) Prediction: RFM analysis provides insights into customer behavior and purchasing patterns, allowing marketers to estimate the customer lifetime value. By understanding the value and engagement level of different customer segments, businesses can allocate resources more effectively and prioritize efforts to acquire and retain high-value customers.
4. Product Recommendations: RFM analysis can also be used to generate personalized product recommendations. By understanding a customer’s past purchasing behavior, marketers can recommend products that align with their preferences, increase cross-selling opportunities, and enhance the overall customer experience.
5. Churn Prediction: RFM analysis can help identify customers who are at risk of churn (i.e., discontinuing their relationship with the brand). By monitoring changes in RFM scores over time, businesses can proactively target and engage customers who show signs of decreased engagement, offering incentives or personalized interventions to prevent churn.
RFM analysis provides a data-driven approach to segmenting and understanding customer behavior, allowing marketers to make informed decisions, optimize marketing efforts, and enhance customer satisfaction and loyalty.
A wide assortment of perspectives shot over a bit more than a decade. John delves into the positives and negatives of RFM, how to build it, how to apply it, how to make money with it and how to go far beyond it. The videos are arranged from most recent first (so you may want to watch them in reverse order).
Jim’s Intro: Here’s a more complex model using Recency and Frequency to rank the LifeTime Value and likelihood to respond of customers relative to each other.
Have you ever heard somebody refer to his or her customer list as a “file”? If you have, you were probably listening to someone who has been around the catalog block a few times. Before computers (huh?), catalog companies used to keep all their customer information on 3 x 5 cards.
I was recently asked to evaluate how a catalog selects names for upcoming mailings. The Executive told me that her vendor asked her company to switch from model-based selections to … are you ready for this … to RFM … prompting me to offer a predictable response.
And I laughed and laughed. What idiots! My goodness. The vendor community is really failing my client base … again.
One problem.
In my arrogance, I forgot the original request – to evaluate how this company should select names for catalog mailings.
So I evaluated models against the RFM strategy.
The RFM strategy performed to within 0.3% of the prior modeling strategy – a modeling strategy that while not outstanding was at least credible.
An overview of RFM. Recency, Frequency; Monetary (RFM) continue to form the basis of many behavior analysis variables. Learn about the Direct Marketing basics of RFM in this series of videos.
Recency, Frequency, Monetary value. The calculation of scores based on these three transactional variables has a lot of sway over the minds of fundraisers, and I just don’t understand why.
It’s one of those concepts that never seems to go away. Everyone wants a simple way to whip up an RFM score. Yet anyone who can do a good job of RFM is probably capable of doing real predictive modeling. The persistence of RFM seems to rest on some misconceptions, which I want to address today.
