+ Home
+ Subscriptions
+ Archives
+ Resources
+ Contact Us
+ In The News
+ GAP Home

logo-3.gif (4379 bytes) Click Here For Your Free Subscription

Home +

menu_hr.gif (1966 bytes)

+++ S P E C I A L R E P O R T +++
"Measuring Customer Retention and Value in Online Retailing"
By Jim Novo
October 18, 2000


How is it the catalogs, and their distant cousins the TV Shopping Networks, are virtually the only profitable major B2C retailers on the Internet? The Direct Marketing Association's latest study of catalogs with web sites found 69% of them were making profits online.

Catalog and TV Shopping marketers have understood for a very long time that it is much less expensive to retain customers than it is to acquire new ones. They have been doing business with this philosophy for decades. Customer acquisition is certainly important; if you don't do it, the business eventually dies. So why focus on customer retention?

Because by understanding customer retention behavior, catalogs lower their customer acquisition costs. It's all tied together. Sure, there has to be a "first shot" somewhere, the initial push for customers. But even this effort is based on what is known generally about customer retention in the catalog business. It's done by marketing to people who are known customers of other catalogs, usually by renting a list of customers from a catalog offering related products. The reason? Customers of other catalogs are the most likely to respond to a new catalog, and most likely to be repeat customers. The secret to good customer retention is to acquire the right customers in the first place.

So understanding customer retention is extremely important to the entire direct selling model of doing business with consumers, both for customer acquisition and retention. Good retention marketers have two objectives with any kind of customer retention marketing:

1. Hold on to the most valuable customers

2. Try to make less valuable customers more valuable

To retain and increase the value of customers, you have to create marketing promotions and execute them. To do this in the most efficient and effective way, you have to know the value of your customers and their likelihood to respond to a promotion, for these 2 reasons:

1. You don't want to waste money on promoting to low value customers because you can't make a profit

2. You don't want to waste money promoting to customers who won't respond because this is just throwing money away.

Customer Retention and Valuation Concepts

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.

They'd rifle through this deck of cards to select customers for each mailing, and when a customer placed an order, they would write it on the customer's card. These file cards as a group became known as "the customer file", and even after everything became computerized, the name stuck.

Who cares? It happens that while going through these cards by hand, and writing down orders, the catalog folks began to see patterns emerge:

1. Customers who purchased _Recently_ were more likely to buy again versus customers who had not purchased in a while

2. Customers who purchased _Frequently_ were more likely to buy again versus customers who had made just one or two purchases

3. Customers who had spent the most _Money_ in total were more likely to buy again. The most valuable customers tended to continue to become even more valuable.

So the catalog folks tested this concept, the idea past purchase behavior could predict future results. First, they ranked all their customers on these 3 attributes, sorting their customer records so that customers who had bought most Recently, most Frequently, and had spent the most Money were at the top. These customers were labeled "best". Customers who had not purchased for a while, had made few purchases, and had spent little money were at the bottom of the list, labeled "worst".

Then they mailed their catalogs to all the customers, just like they usually do, and tracked how the group of people who ranked highest in the 3 categories above (best) responded to their mailings, and compared this response to the group of people who ranked lowest (worst). They found a huge difference in response and sales between best and worst customers. Repeating this test over and over, they found it worked every time!

The group who ranked "best" in the 3 categories above always had higher response rates than the group who ranked "worst". It worked so well they cut back on mailing to people who ranked worst, and spent the money saved on mailing more often to the group who ranked best. And their sales exploded, while their costs remained the same or went down. They were increasing their marketing efficiency and effectiveness by targeting to the most responsive, highest value customers.

The Recency, Frequency, Monetary (RFM for short) customer model works everywhere, in virtually every retail-oriented business. And it works for just about any kind of "action-oriented" behavior you are trying to get a customer to repeat, whether it's purchases, visits, sign-ups, surveys, games or anything else. I'm going to use purchases and visits as examples.

A customer who has visited your site Recently (R) and Frequently (F) and created a lot of Monetary value (M) through purchases is much more likely to visit and buy again. And, a high Recency / Frequency / Monetary (RFM) customer who stops visiting is a customer who is finding alternatives to your site. It makes sense, doesn't it? Customers who have not visited or purchased in a while are less interested in you than customers who have done one of these things recently. Put Recency, Frequency, and Monetary value together and you have a pretty good indicator of interest in your site at the customer level. This is valuable information to have.

Assuming the behavior being ranked (purchase, visit) using RFM has economic value, the higher the RFM score, the more profitable the customer is to the business now and in the future. High RFM customers are most likely to continue to purchase and visit, AND they are most likely to respond to marketing promotions. The opposite is true for low RFM customers; they are the least likely to purchase or visit again AND the least likely to respond to marketing promotions.

For these reasons, RFM is closely related to another customer direct marketing concept: LifeTime Value (LTV). LTV is the expected net profit a customer will contribute to your business as long as the customer remains a customer. Because of the linkage to LTV, RFM techniques can be used as a proxy for the future profitability of a business.

High RFM customers represent future business potential, because the customers are willing and interested in doing business with you, and have high LTV. Low RFM customers represent dwindling business opportunity, low LTV, and are a flag something needs to be done with those customers to increase their value.

RFM scoring of individual customers is a catalog and TV shopping technique used to select which customers you can most profitably promote to. There is a more simplistic application of RFM online retailers can use to easily track the quality of overall customer retention, without going through the effort of RFM scoring individual customers. We will consider this easier "group tracking" approach in the rest of this report.

If you'd like more information on the individual RFM scoring approach or the validity and use of RFM scoring in general, see the links at the end of this report.

Measuring Overall Customer Retention

A simplified application of RFM is called Hurdle Rate Analysis, where "hurdles" are selected for Recency, Frequency, and Monetary Value, and the entire customer base is evaluated against these hurdles as a group.

A Hurdle Rate is simply the percentage of your customers who have at least a certain activity level for Recency, Frequency, and Monetary Value. It's the _percentage of customers who have engaged in a behavior_ since a certain date (Recency), engaged in the behavior a certain number of times (Frequency), or have purchased a certain amount (Monetary value).

Because of the link between RFM and Lifetime Value, it can be concluded:

If the percentage of customers over each hurdle (Recency, Frequency, Monetary value) is growing, the business is healthy and thriving. Customers are responding positively to the experience they receive, and as a group are more likely to engage in profit generating behavior in the future.

If the opposite is true, and the percentage of customers over each hurdle (Recency, Frequency, Monetary Value) is falling over time, high value customers are defecting and the future value of your business is falling. Customers as a group are responding negatively to the overall service they are receiving.

Sample Hurdle Rate Implementation

If the business has an understanding of the customer LifeCycle, the logical Hurdle Rates to set for Recency, Frequency, and Monetary value would equate to customer behavior at primary changes in the customer LifeCycle.

If the business is very new or has never studied the customer LifeCycle, then a good default position to use is based on the 20/80 rule (20% of customers generally generate 80% of the behavior, be it sales, visits, etc.) The analysis would default to a "starting Hurdle Rate" of 20% for each behavior (purchases, visits), and examine the customer base to determine RFM values corresponding to the 20% hurdle.

In this example, the business would look at the top 20% of their customers for each of the Recency, Frequency, and Monetary value parameters, and examine the "tail end" customers - the bottom customers of the top 20%. These values would become the hurdles the customer base is judged against. Customers would have to have _at least_ the activity of these tail end customers to be considered "over the Hurdle".

For example, in a database of 10,000 customers, to determine the _Recency_ hurdle using the 20/80 rule:

1. Select the behavior to be profiled - purchases, visits, etc.

2. Sort customers by most Recent date of the behavior

3. Starting at the most Recent customer, count down to customer number 2,000 (20% of 10,0000) in this sorted database. Examine the group of customers near this target level, perhaps from customer 1,950 to customer 2,050.

4. Determine _how long ago_ (Recency) these customers, on average, engaged in the behavior you are profiling

5. You find these customers last purchased an average of 60 days ago.

6. The Recency hurdle becomes 60 days for the "today" or starting Hurdle Rate of 20%.

Regardless of whether the Hurdle Rate is set using the customer Lifecycle or the 20/80 rule, the operational implementation is the same. Each week or month, sweep the database and determine the percentage of customers who have engaged in the behavior within the hurdle definition. For a 60-day hurdle, it would be the percentage of customers engaging in the behavior in the past 60 days.

If the percentage of customers "over the hurdle" (engaging in the behavior less than 60 days ago) grows over time, the future value of the customer base (LTV) is rising. If the percentage of customers "over the hurdle" is falling, the future value of the customer base is falling as well.

For example, if you started with 20% of customers having 60 day Recency for purchases, you would like to continue seeing 20% of your customer base purchase in the past 60 days. Ideally, you would see 21%, then 22%, then 23%, and so on, purchase in the past 60 days. If this percentage is rising, this means the future value of your customer base is growing, your high value customers are sticking with you, and your promotions will have increasing response rates.

This calculation can be completed on the same behavior as the Recency exercise was above for Frequency, and if there is a transactional value to the behavior (a purchase), for Monetary Value as well. Additional behaviors can also be monitored simultaneously. On the web, tracking purchases and visits together would make sense. Unless the business has a very clear understanding of revenue per visit across different areas of the site, it is unlikely tracking the Monetary value of visits would be very useful but Recency and Frequency would be very important.

These Hurdle Rate percentages can be graphed over time, and trends established. Clearly there will be fluctuations up and down, and seasonality in retail or event oriented businesses. But if solid trends in Hurdle Rates develop in either direction, or year over year comparisons are dramatically different for a seasonal business, the measurement should be judged to be significant and actionable.

Graphing Hurdle Rates over time provides an easy way to present a somewhat complex subject to management or investors: lines going up = good, lines going down = bad.

If would like to see an example of a Hurdle Rate chart as described above, follow the link below and read the description under the chart:


A business can mix and match tracking of behaviors and Hurdle Rates across the RFM metrics according to priorities in the business model. Any important activity at your site can be assessed using RFM Hurdle Rates.

Rising percentages of customers "over the hurdle" represent growing the share of best customers in your customer database for the activity analyzed. Your best customers are remaining with you, and other customers are "growing into" becoming best customers.

If you don't see this rise in percentages, the future value of your business is shrinking. Higher customer activity levels among best customers are just not continuing; this trend should be researched further and action taken to counteract the decline.

A very effective way to take action on declining Hurdle Rates, if you choose to continue to follow the RFM methodology, would be to score individual customers for RFM. If you don't have a problem with customer retention, it's probably not worth the effort, but if you do, promotions based on individual RFM scores are a very cost effective way to stall the decline in overall customer value. More on this topic is offered below:

For advanced or large companies, with rich activity data on their customers, see the following article written by a senior director at Oracle Corporation. Go to the link below and search for "ROI in CRM"


More information for small or new online retailers about RFM and other database marketing techniques can be found at my site on this page:


Readers who need some confirmation of RFM as a legitimate model and / or more details about classic RFM implementation should search the term "RFM" at these locations:


Jim Novo


Jim Novo, Marketing Mercenary mailto:jim(at)jimnovo.com
Author: Drilling Down - Turning Customer Data into Profits
with a Spreadsheet - http://www.jimnovo.com
Free Drilling Down Newsletter: drillingdown-on(at)mail-list.com 

[GAP Home] [E-Tailer's Digest Home] [Subscriptions] [Resources] [Contact Us] [In The News] [Invite a Friend]


Copyright 1998-2000 GAP Enterprises, Ltd.
Contact webmaster(at)gapent.com with any comments or questions about this site.
Last modified Sunday, February 16, 2003