Database Screams!
DMSI e-NEWSLETTER:
Focus on Analytics: Database Marketing Tips, Careers, & News
Serving 4000+ Marketing Pros Worldwide
In This Issue:
The Professor's Corner:
Top 5 Ways to Misuse and Abuse RFM Analysis
Attention MOM Users: MOM Extractor Shareware Utility Now Available
A New Look at Lifetime Value
How Desktop Marketing
Solutions, Inc. Can Help You!
Dear Friends, 
Stop, Thief!! Imagine using RFM
analysis for crime control: if a criminal offender robbed a bank
recently, robbed banks frequently, and only robbed large banks, should
someone keep an eye on him/her? If you guessed RFM analysis would
predict a resounding “Yes,” you would be correct! This month’s focus on
marketing analytics begins with RFM – which indeed is now being used in
criminal justice as well as marketing. Additionally, we are announcing
the release of our MOM Extractor shareware – a new tool for users of
Mail Order Manager. Finally this month, we are happy to hear from our
colleague, David Raab, about Lifetime Value. I believe that no one has a
better feel for marketing applications – and communicates about them
better – than David.
As always, please let us know how DMSI can fit into your database marketing plans!
Bruce Gregoire,
President and Founder,
Desktop Marketing Solutions, Inc (DMSI)
Adjunct Professor, Marketing Information Systems
Carey School of Business,
Johns Hopkins University Graduate School
The
Professor’s Corner: Top 5 Ways to Misuse and Abuse RFM Analysis
When used properly, RFM analysis (Recency,
Frequency, and Monetary Value) can be a basic but valuable modeling
approach to score your customer base. This scoring is usually done in
advance of a mailing campaign, to help predict a customer’s “likelihood
to respond”. It is noteworthy to mention that, as a measure of human
behavior, it is now being used by fields outside of marketing, including
crime prevention. But like any other tool, RFM can be misused and
abused. Here are the problems that can result from bad assumptions (or
implementation) of RFM:
1. Self-fulfilling prophecy phenomenon: When launching a
campaign, you need to record a snapshot of the RFM values “pre-campaign”
for later analysis, rather than “post-campaign” when you are ready to do
matchback analysis. I have seen DM pros make this mistake.
2. Ruining your Honeymoon. If you are scoring the frequency of
your new customers improperly, you risk ignoring new customers in your
next campaign. New customers – who may have just fallen in love with
your products/services – do not have the high frequency counts as some
of your veteran customers. On a raw frequency basis, their low scores
will not qualify them for your next campaign – a big mistake! Instead,
their frequency counts should be compared and scored with other recent
customers on a peer group basis (not on a raw frequency basis).
3. Tis’ not the Season. Traditional RFM – e.g. using 3 or 6 month
intervals to score Recency – does not work well with seasonal business
models. If your business fits this category, try a quintile or decile
approach instead. Your seasonal spikes of activity will be smoothed out.
4. Long Buying Cycles. RFM works best for businesses selling
consumable items, not as well for businesses with long buying cycles.
The longer cycle makes it harder to time your promotion properly, and
may result in devaluing RFM. But don’t despair - even with a long cycle,
RFM can still provide benefit to you. For instance, consider sales of
accessory items, and reminders to your recent satisfied buyers to refer
their friends/family.
5. RFM - which variable is dominant? In terms of predictive value,
the traditional thinking is that an “R” score trumps “F”, and “F” trumps
“M” (hence, the name RFM rather than MFR or FMR). Emphasizing Recency is
sort of the “what have you done for me lately” approach. But, of course,
every business has different buying patterns, and deserves study to
determine which variables are really dominant (usually with
regression/correlation analysis). A study of one of our client databases
revealed that the influence of the RFM variables was exactly the reverse
of what we expected – namely, M, F, then R. Another client database
showed a $100K order (yes, one order) for a customer who had lapsed for
4 years.
Learn
more: ask us about “Retro RFM”, a new feature in our WiseGuys Marketing
Software. Retro RFM can go back in time to score customers from your old
mail files. Then the good news: with fast and easy multiple regression
analysis, DMSI staff can establish the dominant R-F-M variables for your
specific business (see #5 above). Call our offices at 703-941-8109 for
more info.
Return to top
Attention MOM Users: MOM Extractor Shareware Utility Now Available
If
you are a user of Mail Order Manager (MOM), we have good new for you!
MOM is one of our favorite legacy systems for capturing the
transactional data that marketers need for marketing analytics. And
indeed, since 1999, more than 100 MOM user organizations have turned to
DMSI for help with everything from sales tracking to database marketing.
But getting at the data has become increasingly difficult – especially
with MOM 6.0.
Problem solved – with MOM Extractor! DMSI has developed a shareware
utility that allows you to export key (or all) tables into a .dbf or .csv
format. It even includes an auto-scheduler for overnight or weekend
exports. Now you can grab your MOM data with no muss, no fuss, for use
in your preferred application (including our WiseGuys Marketing
Software).
Learn more: Contact DMSI offices at 703-941-8109, or
WiseGuys@DesktopMarketingInc.com
and we will send you a
copy.
Return to top
A New Look at Lifetime Value
By
David M. Raab
Customer Value. Customer Value, also
called Customer Lifetime Value (CLV) or Lifetime Value (LTV), is the net
present value of the cash flows associated with a customer. In some
ways, it is the ultimate measure of marketing performance. For example,
return on marketing investments should be calculated using the change in
CLV as the “return”.
Sadly, CLV is often viewed as too mysterious or unreliable to use in
this way. Let’s clear away a few of those obstacles.
Calculation Choices
CLV calculations can indeed be complex. One important choice is the time
frame: CLV may include future cash flows, past cash flows, or all flows
throughout the customer lifetime. Future value is appropriate when
judging marketing programs, since those programs can only affect future
results. Past value is easy to calculate but can be misleading. For
example, most college students have low spending histories and little
income, but are aggressively pursued by credit card marketers who know
they will be valuable customers once they graduate.
Another choice is the set of customers to include. In some industries,
all customers have roughly equal value and a single lifetime value
figure is adequate. In other industries, customer values vary greatly.
For example, financial services firms perform customer-level value
calculations so they can treat each person differently depending on what
their business is worth.
Avoid assuming that customers start with a fixed lifetime value which is
depleted over time. Sometimes the value is truly fixed, such as a
parent’s spending on baby food. But more often, year-to-year consumption
is relatively stable regardless of past spending. In situations like the
college student credit cards, future value actually increases over time.
Techniques
The calculations to provide a lifetime value estimate vary depending on
the purpose.
- For strategic analyses such as business acquisitions, a simple formula
based on historical averages may suffice.
- For detailed planning, a typical model assigns customers to tiers
based on when they first ordered or how many times they have purchased.
Each tier has a different retention rate and purchase volume. Lifetime
value is calculated by simulating the flow customers from tier to tier.
This approach can give a precise value for the existing customer base
and can predict the impact of changes in acquisition spending.
- Performance measurement requires actual lifetime values. These are
based on the revenues and expenses of individuals. Data from similar
customers is aggregated to calculate LTV by segment.
Calculations of actual lifetime value require a great deal of data,
which is not always available. In addition, they take time: most
analyses apply a three-to-five year time horizon, but few managers want
to make decisions based on what happened five years ago.
One solution is to combine results for different cohorts. This looks at
first-year retention and spending rates for customers who started in the
previous year, second-year rates for customers who started two years
ago, third-year rates for customers who started three years ago, and so
on. Each rate is based on transactions within the past twelve months, so
they reflect the most recent information available.
Uncertainties
All useful customer value calculations are ultimately estimates. They
are subject to changes in customer mix, business conditions, company
products, and marketing activities. Prudent business people adjust for
these risks through higher discount rates on future cash flows. But they
also recognize that ignoring lifetime value altogether can cost them
money. In one study, my firm found that allocating acquisition budgets
based on cost per order yielded 10 to 20% lower long-term profits than
allocations based on lifetime value. No company should give up that much
value without a fight.
Learn More:
Adapted from
Marketing Performance Measurement Toolkit, by
David Raab. David is a
consultant specializing in marketing technology and analysis. Clients
have included major firms in financial services, retail, communications,
and other industries. Mr. Raab has written hundreds of articles for DM
Review, DM News and other industry publications. Many of these are
available without charge at
www.archive.raabassociatesinc.com
Return to top
How Desktop Marketing Solutions, Inc. Can Help You!
DMSI is a full-service resource for database marketing software, programming, installation and applications. Whether you're considering a new software system or just need help assessing your current one, DMSI can help. The staff at DMSI offer the rare combination of database know-how and direct marketing expertise. Our niche is small to mid-size organizations who need the power of advanced database techniques to grow their business. We provide software product installation and customization for "best of breed" marketing database and CRM packages.
And now, pick up the phone! One call gets you 15 minutes of Free Database Advice
Step 1: Call DMSI offices anytime at (703) 941-8109
Step 2: "Ask the Experts" at DMSI - give us your toughest database question.
Step 3: No charge - no obligation. 15 minutes may be all the help you need to start solving your marketing database problem.
Return to top
Feedback from our readers:
"Great newsletter: It is one of the few I read top to bottom"
Carlie Adams, President, MAC Direct
"The newsletter is terrific. The content was valuable and interesting. Thanks for sending it, and we are looking forward to the next issue already.
Joanna Napolitano, Natural Wellness
See Past Newsletter Issues
Your FREE bi-monthly
E-Newsletter is full of great Database Marketing and CRM resources and
tips.
DMSI E-Newsletter Archives
