sunny1637@gmail.

com
BX9T5ZHNQF

This file is meant for personal use by [email protected] only.

Sharing or publishing the contents in part or full is liable for legal action.
 About the Author

Roy Wollen is president of Hansa Marketing Services. Hansa is an Integrated Marketing Communications
firm that provides customer engagement and intelligence solutions through its brand strategy, market
research, and analytics services.

Using measurement-driven analytics and expert data management techniques, Hansa delivers objective
guidance to help simplify the complexity in marketing systems technology and propel its clients forward
on a clear, concise path toward marketing success.

With over 20 years of analytics and marketing systems experience, Roy has led some of the top marketers in
the country, particularly in b2b, interactive, multi-channel retail, biotech, financial services, and nonprofit.

Prior to 2005, Roy was at Direct Marketing Technology and its parent company Experian, the largest
[email protected]
BX9T5ZHNQFdatabase company in the world. Roy has been on the client side, working for Bloomingdale’s and
Hewlett-Packard, and on the agency side at Ogilvy & Mather.

Roy has a Master of Science degree from Northwestern University’s Medill Integrated Marketing
Communications (IMC) program and is an adjunct professor at DePaul University in Chicago, IL.

For further information about Hansa Marketing, Roy can be reached via
email at [email protected] or by phone at +1 847.491.6682.
Thought leadership content can be found at www.HansaMarketing.com

This file is meant for personal use by [email protected] only.

© Hansa MarketingSharing
Services,
or Inc. – All rights
publishing reserved in part or full is liable for legal action.
the contents 2
 Executive Summary

Despite the current love affair with predictive models, direct marketing’s three-variable formula,
Recency-Frequency-Monetary Value (RFM), still has a place in modern database marketing. RFM
is not a replacement for inferential statistics. But in the real world, RFM can still be useful when
models are not practical. RFM also provides a management summary of customer behavior based
on purchases and plays a role in policing the black-box results of predictive models to ensure quality
before a campaign is implemented.

Segmentation of Customers

What comes to mind when you read these descriptions of customer segments?

s Advocates
s Repeat buyers
s Gift givers
[email protected]
BX9T5ZHNQF
s Too good to be true
o Habitual returners
o Fraud
s Trial buyers
s Once was enough
s Dormant
s Defected
o About to Defect
o Revolving Door
s Cry in your pillow (“please come back”)

Each of these customer segments is rooted in purchase behavior. Purchase behavior is the best
predictor of repeat purchasing and loyalty. While it is measured in different ways, depending on industry
and customer lifecycle, all database marketers covet its empirical facts on how often buyers renew their
subscriptions/memberships, visit your site, and shop at your store. Further, purchase behavior is about
how much they spend, the products/services they buy, and in what combination or sequence. Purchase
behavior codifies both the tenure as well as the recency of your relationship with your customers.

This file is meant for personal use by [email protected] only.

© Hansa Marketing Services, Inc. – All rights
Sharing or publishing reserved in part or full is liable for legal action.
the contents 3
 The good news for today’s marketers is that the most important purchase behavior is already in
your customer database. What can you do with these data? You can:

s Identify groups of customers

s Target them for campaigns
s Promote repeat purchase and loyalty
s Defend against attrition/defection
s Acquire customers who resemble the best ones

Segmentation gives direct marketers a quantifiable way

to distinguish between the best and worst customers
Customers

on file. Purchase behavior is the most powerful way

to segment your customers by historic value.

You can also gain insight with purchase behavior

from outsides sources of information such as co-op
[email protected]
BX9T5ZHNQF databases, which are a collection of hundreds of direct
Segments

marketing lists pooled together; individual response

lists; and any merge/purge processing itself (with its
resulting intra- and inter- matches). These data provide
contextual dimensions and will help you realize there is
more going on in your customers’ lives than just their relationships with you.

Other kinds of segmentation bring you closer to why your customer buys from you, particularly
from primary research that adds their attitudes and experiences. This information, along with
demographics, explains their motivations and brings customer segments to life. This area of
research is the most interesting and strategic, and has an impact on benefits customers seek,
media consumption habits and advertising strategy. It is critical input for decisions around what
to say and how to say it.

Recency – Frequency – Monetary Value (RFM)

Recency Frequency Monetary Value (RFM) is a quick, descriptive way to segment a marketing
database on purchasing behavior that direct marketers have used with success since the 1930s.

This file is meant for personal use by [email protected] only.

© Hansa MarketingSharing
Services,
or Inc. – All rights
publishing reserved in part or full is liable for legal action.
the contents 4
 What is RFM? How do you use it? Is it superior to inferential statistics such as predictive models
and decision trees? Generally, there is no contest against statistical modeling; RFM will lose just
about every time. While this eBook may have just come to a screeching halt, the balance will
argue that RFM still has an important place in today’s modern direct marketing as a complement
to predictive models, particularly for non-statisticians (Figure 1).

Figure 1: RFM advantages over Predictive Models

RFM Predictive Models

Easy for managers to understand Black Box
Can build it yourself Need to hire a statistician or trained data miner
Can build it yourself, now Requires a build process, with analysis and
validation datasets
Portable across industries May be applicable to only one company
Somewhat effective at mitigating Would need a model for each season;
the confounding effect of seasonality ideally one model for each campaign
[email protected]
BX9T5ZHNQFRFM definition is stable and does not Typically, would need to be rebuilt every 2 years
need to be rebuilt or redefined when predictive power decays, or in reaction
to a competitor or marketplace shift
Applies to all customers and supports sortation Doesn’t always apply to all customers
of all customers in the database (by RFM (why score customers you know you
quartiles, quintiles, deciles, duo-deciles, centiles) won’t promote?)
Can use RFM across the organization Additional model may be required for
for reactivation, cross-sell reactivation and cross-sell programs

To be fair, predictive models have critical advantages over RFM. RFM by definition
only utilizes 3 predictor variables, whereas predictive models can interrogate hundreds
or even thousands. Models employ as many independent variables as necessary to
maximize prediction. While many are collinear, the more independent variables, the
more power in predicting future purchase behavior.

The definitive article on “The Superiority of Statistics-Based Predictive Models Versus RFM Cells”
can be found within a library of articles on direct marketing published by Wheaton Group.
http://www.wheatongroupllc.com/library/01_01_01.asp

This file is meant for personal use by [email protected] only.

© Hansa Marketing Services, Inc. – All rights
Sharing or publishing reserved in part or full is liable for legal action.
the contents 5
 If You’re Forced to Choose, Choose ‘Both’

I choose to use both predictive models and RFM side by side. My rationale is that predictive
models do a superior job of predicting sales and my first priority is to make money. Predictive
Models have a better return on investment than segmentations based on RFM.

However, RFM is applicable when modeling isn’t practical. For example, perhaps your database is
too small to warrant the investment in building the model. The fees for building predictive models
can run in the tens of thousands, while RFM is essentially a do-it-yourself proposition; and, as a
result, much cheaper. Finally, building a model takes time, especially since you need to go back
in time, build a regression equation on a group of customers, validate the result on an equivalent
group, implement the model by scoring today’s database, and then pull the trigger. RFM values,
by contrast, can be applied to your database by the time you get to the end of this paper.

My favorite role for RFM is as a management tool. By predictor variables, models gain predictive
power, but lose the ability to explain the reasons why it works. This is a black box for management,
as well as a missed opportunity to understand the key business drivers of the dependent variable
(response, sales per campaign, loyalty). It’s true; there have been admirable steps forward in
[email protected]
BX9T5ZHNQF
pairing up Regression models for predictive power with Principal Component Analysis and tree-
analyses to explain its building blocks. However, these are additional investments in themselves
that require time and money. My suggestion is to use RFM for understanding, in concert with
predictive models for campaign execution.

Validate a Predictive Model with RFM before You Contact Customers

How can you validate that a model is correct before you pull the trigger? What are some basic
diagnostics you can run before you put the offers into the marketplace?

When brings you very attractive F-Statistics and R2 compelling you to roll the dice on your next
campaign, you should verify their work as your first step. First, you’ll be reviewing the decisions
they made with regards to sample sizes, statistical and sampling techniques, treatment of outliers,
treatment of incomplete information (blanks, nulls, garbage), transformation of variables and so on. But
you should also ask for a crosstab comparing their “score” (outcome of the model) versus RFM.

This crosstab should contain not only population counts, but also ratios such as LTD Dollars/Buyer,
Average Order Size, Average Days since Last Purchase, and LTD Orders/Buyer. You’ll be looking for
a correlation between the best scores and the best ratios. If there are attractive ratios in the basement
of your predictive model, you may be missing out on opportunities with good customers.

This file is meant for personal use by [email protected] only.

© Hansa MarketingSharing
Services,
or Inc. – All rights
publishing reserved in part or full is liable for legal action.
the contents 6
 A Modern Take on Recency

It is part of Green Bay Packer folklore that coach Vince Lombardi starting a
training camp, attended by professional athletes, snorted “This, is a football!”
The implication was to start from scratch and re-learn the game (his way).

I’ve always related to that sentiment in a more positive light and interpreted
it to mean learn everything you can about a particular topic, whether
that’s a pulling guard sweep to the weak side (football jargon) or customer
segmentation.

As business people who leverage databases to be better direct marketers, what can Recency, the
R of the RFM model, teach us about our customers and marketing programs?

First, here’s a definition: Recency (R) is defined as the time since last purchase, or meaningful
transaction, that your customer makes. The more recent the last action, the higher the likelihood
your customer will respond to the next e-mail, phone solicitation, direct mail campaign, etc. It is
operationalized as the number of months since the last purchase, but the unit of measure can
[email protected]
BX9T5ZHNQFeasily be changed to weeks or days for online businesses. You should always use the update date
or the high date1 on the database, not “today’s” date.

What is the Date of Last Purchase that makes sense for your business?
s Most Recent purchase at the store
s Most Recent website purchase
s Most Recent catalog purchase (your catalog)
s Most Recent purchase in division X of your corporation
s Most Recent purchase across all divisions (aka “Corporate Recency”)
s Most Recent catalog purchase (across all catalogs in a co-op database)
o Z24, Prefer Network, Abacus, I-Behavior, Next Action, b2bBase, MeritBase

s B2b Recency has its own special application of recency:

o When the individual made their last purchase
o When the company made its last purchase (Most recent date across all individuals)

s Last point earning or award activity on the web

s Last installment date on a continuity club

Recency has important business applications beyond segmentation. It is a key business dimension
and can be triangulated (same customer - two recency dates) to see customers with a deeper
understanding. (See Figure 2.)
In database marketing, a database is sometimes called “Names through x” where x is the most recent purchase date
I.

observed or the update date.

This file is meant for personal use by [email protected] only.
© Hansa Marketing Services, Inc. – All rights
Sharing or publishing reserved in part or full is liable for legal action.
the contents 7
 Figure 2: Recency can be applied beyond RFM Segmentation when it’s “triangulated”

Recency Date Triangulated with Application

Last Purchase Date Frequency – Monetary Value RFM Segmentation
Last Web Date Last Store Visit Channel Preference
Each channel’s recency,
in what combination, will describe
a customer segment
Last Web Date Corporate Recency Reactivation
If identical, web was most recent.
If not, customer bought in another
channel and (depending on size of
difference) candidate for reactivation
Division 1 Recency Division 2 Recency Cross-Sell experiments
Individual Recency (b2c) Household Recency Cost Reduction
Mail one per HH
Individual Recency (b2b) Site Recency or Topic for another time
Parent Company Recency
Your company’s recency Co-op Recency Reactivation
[email protected]
BX9T5ZHNQFNon Buyer Co-op Recency Acquisition
(no purchase recency) Better Recency on Co-op
indicates better target
Non Buyer List Recency (“selects”) Acquisition
(no purchase recency) Better “selects” indicates better
target (e.g., “hotline” names
bought within last 90 days)
Recency Products Purchased Product Recommendations
“People who bought x also
bought y” recommender systems
Last Ship Date for Series # of installments Tenure promotion
Last Order Date # of remaining items in series Expected date
when supply runs out
Last Subscription Date # of issues in subscription Renewal Campaigns
Last Response Date NCOA move date Winback campaign
Last Response Date Job Change date Bring us with you campaign
Last Purchase Date Item Shipment Date(s) Fulfillment issue?
Last Purchase Date Pattern of Purchase Dates Seasonality, Velocity, Segmentation
(gift giver?)
Last Purchase Date Time going by without Retention campaign
repeat purchase
Last Purchase Date First Purchase Date Tenure and Loyalty analysis

This file is meant for personal use by [email protected] only.

© Hansa MarketingSharing
Services,
or Inc. – All rights
publishing reserved in part or full is liable for legal action.
the contents 8
 Show Me the Data

A report card on a season’s worth of campaigns can illustrate the power of Recency on its
ability to segment customers on response rate and sales. This simulation is a powerful way
to understand the range of quality of your customers (See Figure 3). I’m presenting this as a
management summary, not as a suggestion on how to execute your campaigns.

Figure 3: Response Summary by Recency

Response Summay by Recency

Last Purchase 6 Month Season % Sales/
Customers
Recency Campaigns Visits Revenue Resp. Piece

0-3 Months 170862 1215314 49401 $21797541 4.10% $17.94

Best
4-6 Months 128238 1034895 21715 $8552928 2.10% $8.26

7-12 Months 202443 1436914 21004 $8102208 1.50% $5.64

13-18 Months
[email protected] 178411 912021 7217 $2636832 0.80% $2.89
BX9T5ZHNQF
19-24 Months 154214 592846 3812 1259712 0.60% $2.12

25-36 Months 294001 641028 3105 $1071216 0.50% $1.67

37-48 Months 141888 226515 857 $239701 0.40% $1.06

Worst
49-60 Months 46071 72184 215 $74715 0.30% $1.04

Total 1316128 6131717 107327 $43734853 1.80% $7.13

It is clear to see that “sales per piece” and its first cousin “response rate” march to the beat set
by Last Purchase Date, the row in this report. As managers, we’re looking for ways to distinguish
between good and bad customers. Clearly, the recent customers (0-3 months since their last
purchase) are superior to the dormant customers (no purchase in 2 years).

This can be charted on dimensions including revenue per buyer as well as contribution margin
per buyer (especially as it relates to a threshold for breaking even). See Figure 4.

This file is meant for personal use by [email protected] only.

© Hansa Marketing Services, Inc. – All rights
Sharing or publishing reserved in part or full is liable for legal action.
the contents 9
 Figure 4: The power of Recency illustrated

$25.00
Customer segments with more
recent purchases garner more
$20.00
attractive results (sales per piece)
from a 6-month campaign.
$15.00
Sales/Piece

Charting sales per piece

$10.00

illustrates the range from a high of

$18 (for 0-3M customers) to a low
$5.00
of $1 (for 19M+).

$0.00
0 - 3 Months 4 - 6 Months 7 - 12 Months 13 - 18 Months 19 - 24 Months 25 - 36 Months 37 - 48 Months 49 - 60 Months

$60.00
Margin per buyer can also
[email protected]
BX9T5ZHNQF be charted to illustrate which
$50.00

customer segments are above the

$40.00
breakeven threshold, where the
campaigns cover costs.
Margin per Buyer

$30.00

$20.00
Those segments that are below
breakeven should be suppressed;
$10.00 Breakeven the investment re-allocated to
better segments or pocketed as
$0.00
0 - 3 Months 4 - 6 Months 7 - 12 Months 13 - 18 Months 19 - 24 Months 25 - 36 Months 37 - 48 Months 49 - 60 Months earnings.

This file is meant for personal use by [email protected] only.

© Hansa MarketingSharing
Services,
or Inc. – All rights
publishing reserved in part or full is liable for legal action.
the contents 10
 A Modern Take on Frequency

Frequency (F) is defined as how often a buyer has a dollar earning transaction. It is typically
a “Life to Date” field, and thus would be the accumulation of all transactions from an original
date to the update date. This value includes the original transaction (e.g., enrollment event, first
purchase, etc).

The modern take on Frequency is that it is more interesting to understand the difference between
1x and 2x, versus 10x and 11x. That may seem odd, especially since the 10 time buyers are your
loyal advocates, and they are disproportionately important to the health of your business. That’s
true, however, when planning campaigns the trial buyers need all the help they can get from your
customer database and beyond. (Using RFM, I’m defining 0-3M 1x as a trial customer, whereas
19M + 1x is a goner for most businesses).

What else can we use for 1x buyers? I’ve found several important clues as to which one-time
trial buyers will blossom into advocates and which won’t. Here are some idea starters:
s Depth: # items
s Breadth:
[email protected] # of departments (distinct “aisles” in the store)
BX9T5ZHNQF
s Price points
s Demographics - Geography (zip code, clusters) is more important for 1x buyers
(and critical for 0x buyers)
s Contextual information
s From co-op databases
o 1x for you; 10x for your competitors
o 1x for you; new to catalog shopping

s From the merge/purge

o Match to rentals (1x with lots of matches is far more promising
than 1x with no matches)
o “Multi-Buyers”: 1x multi buyer is a customer who did not match another list
in a merge/purge
s 2x multi matched 1 other list
s 3x multi matched 2 other lists
s From the a b2b site
o 1x buyer in a loyal, high-revenue site is more promising (and may already
be a specifier-decision maker) than a 1x buyer in a new 1-buyer site.
s Source of the customer
s Self-selection (did they come to you, or did you bribe their first purchase with
a $-off coupon?)
This file is meant for personal use by [email protected] only.
© Hansa Marketing Services, Inc. – All rights
Sharing or publishing reserved in part or full is liable for legal action.
the contents 11
 Figure 5: Response Summary by Recency and Frequency

Response Summay by Recency - Frequency

6 Month Season % Sales/
Recency Frequency Customers
Campaigns Visits Revenue Resp. Piece

0-3 Months 3x+ 90802 713249 37508 $17147029 5.30% $24.04

0-3 Months 2x 29595 188862 5360 $2115413 2.80% $11.20
0-3 Months 1x 50465 313203 6533 $2535099 2.10% $8.09
Subtotal 0-3 Months 170862 1215314 49401 $21797541 4.10% $17.94

4-6 Months 3x+ 58251 513520 14231 $5835189 2.80% $11.36

Best
4-6 Months 2x 23920 188644 3139 $1137168 1.70% $6.03
4-6 Months 1x 46067 332731 4345 $1580571 1.30% $4.75
Subtotal 4-6 Months 128238 1034895 21715 $8552928 2.10% $8.26

7-12 Months 3x+ 81972 666277 12293 $4944773 1.80% $7.42

7-12 Months 2x 40365 280555 3764 $1371733 1.30% $4.89
7-12 Months 1x 80106 490082 4947 $1785701 1.00% $3.64
Subtotal 7-12 Months 202443 1436914 21004 $8102208 1.50% $5.64

13-18 Months 3x+ 60541 375304 3695 $1406123 1.00% $3.75

13-18 Months 2x 37628 192206 1465 $531979 0.80% $2.77
13-18 Months 1x 80242 344511 2057 $698731 0.60% $2.03 Worst
Subtotal 13-18 Months 178411 912021 7217 $2636832 0.80% $2.89

[email protected]
19+ Months 3x+ 129024 398968 2687 $949888 0.70% $2.38
BX9T5ZHNQF 19+ Months 2x 127003 313473 1816 $598560 0.60% $1.91
19+ Months 1x 380147 820132 3487 $1096891 0.40% $1.34
Subtotal 19+ Months 636174 1532573 7990 $2645339 0.50% $1.73

Total 1316128 6131717 107327 $43734864 1.80% $1.78

Breaking down Recency ranges by Frequency ranges will add to your understanding of your
customers. Not all 1x buyers are bad (particularly the more recent ones). Not all 3x+ buyers are
loyal (particularly the less recent ones).

This file is meant for personal use by [email protected] only.

© Hansa MarketingSharing
Services,
or Inc. – All rights
publishing reserved in part or full is liable for legal action.
the contents 12
 Figure 6: The power of Recency and Frequency illustrated

$25.00
Again, segments with better RF
scores garner more attractive
$20.00
results (sales per piece) from a
6-month campaign.
$15.00
Sales/Piece

Sales per piece now range from

$10.00
a high of $24 (for 0-3M 3x+) to a
low of $1.34 (for 19M+ 1x).
$5.00

$0.00
0-3M 3x+ 0-3M 2x 0-3M 1x 4-6M 3x+ 4-6M 2x 4-6M 1x 7-12M7-12M 2x 7-12M 1x 13-18M 13-18M 13-18M 19+M 3x+ 19+M 2x 19+M 1x
3x+ 3x+ 2x 1x

$80.00

[email protected] Charting margin per buyer

BX9T5ZHNQF$70.00
gives marketing managers more
$60.00
information to make campaign
decisions.
$50.00
Margin/Buyer

$40.00

Viewing the chart with RF scores

$30.00
on its x-axis now illustrates that
$20.00 the 1x portion of the 13-18M
$10.00 Breakeven
segment is below breakeven,
but repeat buyers in the same
$0.00
0-3M 3x+ 0-3M 2x 0-3M 1x 4-6M 3x+ 4-6M 2x 4-6M 1x 7-12M
3x+
7-12M 2x 7-12M 1x 13-18M
3x+
13-18M
2x
13-18M 19+M 3x+ 19+M 2x 19+M 1x
1x recency ranges are above.

This file is meant for personal use by [email protected] only.

© Hansa Marketing Services, Inc. – All rights
Sharing or publishing reserved in part or full is liable for legal action.
the contents 13
 A Modern Take on Monetary Value

Monetary Value (M) is the sum of all revenue earned. A judgment is used to decide between “Life
to Date” dollars, “Average” dollars, or some dollar amount over time (“0-12 month” dollars).

Adding the third leg of the RFM triumvirate makes our charts resemble what’s called a scree-
plot. Scree plots borrow their name from the junk that falls off very high mountains. The RFM
chart now looks like giant peaks of high customer value compared with run off of lower value
segments. See if you agree: compared to your best customers, everybody else is just scree.

Figure 7: The power of RFM illustrated

$70.00

$60.00

$50.00
Top 10
[email protected]
BX9T5ZHNQF
$40.00
Sales/Piece

$30.00

$20.00

...Scree
$10.00

$0.00
Be 50%

Be 50%

Be 50%

Be 50%

Be 50%

Be 50%

Be 75%

Be 75%
Be 75%

Be 75%

Be 75%

%
st

st

st

st

st

ex est st
N Bes 5%

N Bes 5%

es %
Be 5%

W t

W t
st

W t
st

st
s

s
Be

Be

Be

Be

Be

or

or

or

or

or

or
75
t B t 25

t B 25

t B t 25
tB B

t2

W
st

st

st

st

st

st

st

st

st
st

st

st
e x est

e x est
t

t
ex

ex

ex
N

Some might call this the proverbial “80/20” rule. My colleague Chris Pickering calls it “Pickering’s
Law of Disproportionate Value,” which is only fair given that the definitive book on RFM is called:
Libey and Pickering on RFM and Beyond, published by MeritDirect Press.

This file is meant for personal use by [email protected] only.

© Hansa MarketingSharing
Services,
or Inc. – All rights
publishing reserved in part or full is liable for legal action.
the contents 14
 RFM Model

The biggest complaint about RFM models is the use of cells and the unwieldy number some RFM
models produce. A large number of cells defeats the purpose of ease of use for management
understanding.

Recommendation

s #REATE A CONTINUOUS 2&- SCORE FOR EACH CUSTOMER ON YOUR DATABASE WHEN PREDICTIVE
models are not practical (How? See below).

s 5SE A CELL BASED APPROACH TO PROVIDE AN EASY TO UNDERSTAND SUMMARY OF PURCHASE

behavior, track customers over time plus demystify and police the black-box results of
predictive models.

Rather than
[email protected] create a cell-based approach to RFM (where R would have month ranges such as
BX9T5ZHNQF
0-3, 4-6, 7-12 …, F would have ranges like 1x, 2x, 3x+, and so on), the breakthrough thinking
is to create a continuous RFM score for each customer on your database. This score is one
value for each customer and lends itself to sortation of the customers by value, and the decile
summaries and gains charts that follow.

The formula is taken from the seminal article on the subject called “A Direct Mail Customer
Purchase Model” by Connie L. Bauer, Journal of Direct Marketing, Summer, 1988.

The simple version of the model is RFM Score = 1 F  M

R
... where R is Recency of Last Transaction in Months; F is Number of Purchases, Transactions or
meaningful buying events; and M is a sum of monetary value from the customer.

This file is meant for personal use by [email protected] only.

© Hansa Marketing Services, Inc. – All rights
Sharing or publishing reserved in part or full is liable for legal action.
the contents 15
 In this formula, Recency is a negatively accelerating curve that can be illustrated as follows:

100%
90%
80%
Coefficient in RFM Model

70%
60%
50%
40%
30%
20%
10%
0%
1 2 3 4 5 6 7 8 9 10 11 12

Recency in Months

[email protected]
BX9T5ZHNQF
Mathematically, Recency has the most powerful effect on the RFM score (e.g., Best recency is
1/1 and will not affect the RFM model; Next best recency is ½ and will reduce the RFM score by
50%; Next best is 1/3 and will reduce is by 66%; Inactive customers might have 1/13 and will
reduce the score by more than 90%).

It’s important to keep zeros out of this equation, so either remove non-buyers or add the value 1 to each
component as needed. A square root is used to scale down the effect of M, into the neighborhood of
Recency and Frequency values, and ensure that it doesn’t bully the RFM score result.

Steps in building an RFM model

1. Remove outliers, fraud, employees, suppressions, opt-outs
2. Decide how you will treat non-buyers
3. Build the model, QC a handful of records
4. Create a RFM score for each customer on the database
5. Rank the entire database on this RFM score
6. Divide into equal groups (deciles, duo-deciles, centiles)
7. Repeat after each update

This file is meant for personal use by [email protected] only.

© Hansa MarketingSharing
Services,
or Inc. – All rights
publishing reserved in part or full is liable for legal action.
the contents 16
 Best Practices for using RFM

s 5SE COMMON SENSE 7ITH DURABLE GOODS AND LARGE TICKET ITEMS CARS FURNITURE ETC 2&-
may actually work in the reverse (where less recent is better than more recent). This may also
be true with seasonal businesses. Also, be flexible in how you operationalize the values within
the RFM model. For example, web marketing and e-commerce have their own RFM. Recency
may be measured in days, not months. Frequency may turn into how frequently a visitor
returns to your site, what they purchase or view and where they click. M might be extended
to include what’s in the shopping cart (before abandons).

s 3EASONALITY MAKES DElNING THE 2 RANGES A CHALLENGE $OES YOUR  - RANGE INCLUDE h"ACK
to School,” “Valentine’s Day,” “Holiday Shopping”?

s !UGMENT 2&- WHERE YOU CAN IF IT HELPS YOU UNDERSTAND YOUR BUSINESS DYNAMICS "OB
Kestnbaum pioneered the concept of RFMP, adding a product dimension to RFM. Kestnbaum
called it “FRAC” where “Frequency” was the first variable since he thought it was most predictive,
“A” was “Average Dollars,” and “C” was “Category of Purchase.” His rationale is sound: The
[email protected]
BX9T5ZHNQF best predictor of future Product A purchases is past Product A purchases. This addresses

the challenge of seasonality. Your key business levers are also viable candidates to extend the
simple RFM summary. For b2c direct marketing, this might be RFMIncome. For b2b, this might
be RFMIndustry. Both might see benefits in an RFMChannel segmentation scheme.

s %XTEND 2&- FOR ACQUISITION MARKETING 2&- CAN ALSO BE PUT TO WORK TO ACQUIRE NEW CUSTOMERS
There is some current thinking on calculating RFM for each zip code on file to target prospects
based on observed RFM for customers that live in the neighborhood.

RFM is not a replacement for inferential statistics. It should add value in its unique ability to add
management understanding, ensure data quality, and substitute for predictive models when
models are not practical. RFM has a role in modern direct marketing.

Roy Wollen is president of Hansa Marketing Services. Hansa is a leading provider of Customer
Intelligence services through measurement-driven analytics and expert data management
techniques.
By providing objective guidance to help simplify the complexity in marketing systems technology,
we propel our clients forward on a clear, concise path to marketing success.
For further information about Hansa, please visit us on the web at www.hansamarketing.com,
contact us via email at [email protected], or call us at +1 847.491.6682

This file is meant for personal use by [email protected] only.

© Hansa Marketing Services, Inc. – All rights
Sharing or publishing reserved in part or full is liable for legal action.
the contents 17