. 7
( 137 .)


A Controlled Experiment in Retention 609

The Data 611

The Findings 613

The Proof of the Pudding 614

Lessons Learned 614

Index 615



Why and What Is Data Mining?

In the first edition of this book, the first sentence of the first chapter began with
the words “Somerville, Massachusetts, home to one of the authors of this book,
. . .” and went on to tell of two small businesses in that town and how they had
formed learning relationships with their customers. In the intervening years,
the little girl whose relationship with her hair braider was described in the
chapter has grown up and moved away and no longer wears her hair in corn­
rows. Her father has moved to nearby Cambridge. But one thing has not
changed. The author is still a loyal customer of the Wine Cask, where some of
the same people who first introduced him to cheap Algerian reds in 1978 and
later to the wine-growing regions of France are now helping him to explore
Italy and Germany.
After a quarter of a century, they still have a loyal customer. That loyalty is
no accident. Dan and Steve at the Wine Cask learn the tastes of their customers
and their price ranges. When asked for advice, their response will be based on
their accumulated knowledge of that customer™s tastes and budgets as well as
on their knowledge of their stock.
The people at The Wine Cask know a lot about wine. Although that knowl­
edge is one reason to shop there rather than at a big discount liquor store, it is
their intimate knowledge of each customer that keeps people coming back.
Another wine shop could open across the street and hire a staff of expert
oenophiles, but it would take them months or years to achieve the same level
of customer knowledge.

2 Chapter 1

Well-run small businesses naturally form learning relationships with their
customers. Over time, they learn more and more about their customers, and
they use that knowledge to serve them better. The result is happy, loyal cus­
tomers and profitable businesses. Larger companies, with hundreds of thou­
sands or millions of customers, do not enjoy the luxury of actual personal
relationships with each one. These larger firms must rely on other means to
form learning relationships with their customers. In particular, they must learn
to take full advantage of something they have in abundance”the data pro­
duced by nearly every customer interaction. This book is about analytic tech­
niques that can be used to turn customer data into customer knowledge.

Analytic Customer Relationship Management

It is widely recognized that firms of all sizes need to learn to emulate what
small, service-oriented businesses have always done well”creating one-to-
one relationships with their customers. Customer relationship management is
a broad topic that is the subject of many books and conferences. Everything
from lead-tracking software to campaign management software to call center
software is now marketed as a customer relationship management tool. The

focus of this book is narrower”the role that data mining can play in improv­
ing customer relationship management by improving the firm™s ability to form
learning relationships with its customers.
In every industry, forward-looking companies are moving toward the goal
of understanding each customer individually and using that understanding to
make it easier for the customer to do business with them rather than with com­
petitors. These same firms are learning to look at the value of each customer so
that they know which ones are worth investing money and effort to hold on to
and which ones should be allowed to depart. This change in focus from broad
market segments to individual customers requires changes throughout the
enterprise, and nowhere more than in marketing, sales, and customer support.
Building a business around the customer relationship is a revolutionary
change for most companies. Banks have traditionally focused on maintaining
the spread between the rate they pay to bring money in and the rate they
charge to lend money out. Telephone companies have concentrated on
connecting calls through the network. Insurance companies have focused on
processing claims and managing investments. It takes more than data mining
to turn a product-focused organization into a customer-centric one. A data
mining result that suggests offering a particular customer a widget instead of
a gizmo will be ignored if the manager™s bonus depends on the number of giz­
mos sold this quarter and not on the number of widgets (even if the latter are
more profitable).

Why and What Is Data Mining? 3

In the narrow sense, data mining is a collection of tools and techniques. It is
one of several technologies required to support a customer-centric enterprise.
In a broader sense, data mining is an attitude that business actions should be
based on learning, that informed decisions are better than uninformed deci­
sions, and that measuring results is beneficial to the business. Data mining is
also a process and a methodology for applying the tools and techniques. For
data mining to be effective, the other requirements for analytic CRM must also
be in place. In order to form a learning relationship with its customers, a firm
must be able to:
Notice what its customers are doing

Remember what it and its customers have done over time

Learn from what it has remembered

Act on what it has learned to make customers more profitable

Although the focus of this book is on the third bullet”learning from what
has happened in the past”that learning cannot take place in a vacuum. There
must be transaction processing systems to capture customer interactions, data
warehouses to store historical customer behavior information, data mining to
translate history into plans for future action, and a customer relationship strat­
egy to put those plans into practice.

The Role of Transaction Processing Systems
A small business builds relationships with its customers by noticing their
needs, remembering their preferences, and learning from past interactions how
to serve them better in the future. How can a large enterprise accomplish some­
thing similar when most company employees may never interact personally
with customers? Even where there is customer interaction, it is likely to be with
a different sales clerk or anonymous call-center employee each time, so how
can the enterprise notice, remember, and learn from these interactions? What
can replace the creative intuition of the sole proprietor who recognizes cus­
tomers by name, face, and voice, and remembers their habits and preferences?
In a word, nothing. But that does not mean that we cannot try. Through the
clever application of information technology, even the largest enterprise can
come surprisingly close. In large commercial enterprises, the first step”noticing
what the customer does”has already largely been automated. Transaction pro­
cessing systems are everywhere, collecting data on seemingly everything. The
records generated by automatic teller machines, telephone switches, Web
servers, point-of-sale scanners, and the like are the raw material for data mining.
These days, we all go through life generating a constant stream of transac­
tion records. When you pick up the phone to order a canoe paddle from L.L.
4 Chapter 1

Bean or a satin bra from Victoria™s Secret, a call detail record is generated at the
local phone company showing, among other things, the time of your call, the
number you dialed, and the long-distance company to which you have been
connected. At the long-distance company, similar records are generated
recording the duration of your call and the exact routing it takes through the
switching system. This data will be combined with other records that store
your billing plan, name, and address in order to generate a bill. At the catalog
company, your call is logged again along with information about the particu­
lar catalog from which you ordered and any special promotions you are
responding to. When the customer service representative that answered your
call asks for your credit card number and expiration date, the information is
immediately relayed to a credit card verification system to approve the trans­
action; this too creates a record. All too soon, the transaction reaches the bank
that issued your credit card, where it appears on your next monthly statement.
When your order, with its item number, size, and color, goes into the cata-
loger™s order entry system, it spawns still more records in the billing system
and the inventory control system. Within hours, your order is also generating
transaction records in a computer system at UPS or FedEx where it is scanned
about a dozen times between the warehouse and your home, allowing you to
check the shipper™s Web site to track its progress.
These transaction records are not generated with data mining in mind; they
are created to meet the operational needs of the company. Yet all contain valu­
able information about customers and all can be mined successfully. Phone
companies have used call detail records to discover residential phone numbers
whose calling patterns resemble those of a business in order to market special
services to people operating businesses from their homes. Catalog companies
have used order histories to decide which customers should be included in
which future mailings”and, in the case of Victoria™s secret, which models
produce the most sales. Federal Express used the change in its customers™
shipping patterns during a strike at UPS in order to calculate their share of
their customers™ package delivery business. Supermarkets have used point-of-
sale data in order to decide what coupons to print for which customers. Web
retailers have used past purchases in order to determine what to display when
customers return to the site.
These transaction systems are the customer touch points where information
about customer behavior first enters the enterprise. As such, they are the eyes
and ears (and perhaps the nose, tongue, and fingers) of the enterprise.

The Role of Data Warehousing
The customer-focused enterprise regards every record of an interaction with a
client or prospect”each call to customer support, each point-of-sale transac­
tion, each catalog order, each visit to a company Web site”as a learning
opportunity. But learning requires more than simply gathering data. In fact,
Why and What Is Data Mining? 5

many companies gather hundreds of gigabytes or terabytes of data from and
about their customers without learning anything! Data is gathered because it
is needed for some operational purpose, such as inventory control or billing.
And, once it has served that purpose, it languishes on disk or tape or is
For learning to take place, data from many sources”billing records, scanner
data, registration forms, applications, call records, coupon redemptions,
surveys”must first be gathered together and organized in a consistent and
useful way. This is called data warehousing. Data warehousing allows the enter­
prise to remember what it has noticed about its customers.

T I P Customer patterns become evident over time. Data warehouses need to
support accurate historical data so that data mining can pick up these critical

One of the most important aspects of the data warehouse is the capability to
track customer behavior over time. Many of the patterns of interest for customer
relationship management only become apparent over time. Is usage trending up
or down? How frequently does the customer return? Which channels does the
customer prefer? Which promotions does the customer respond to?
A number of years ago, a large catalog retailer discovered the importance of
retaining historical customer behavior data when they first started keeping
more than a year™s worth of history on their catalog mailings and the
responses they generated from customers. What they discovered was a seg­
ment of customers that only ordered from the catalog at Christmas time. With
knowledge of that segment, they had choices as to what to do. They could try
to come up with a way to stimulate interest in placing orders the rest of the
year. They could improve their overall response rate by not mailing to this seg­
ment the rest of the year. Without some further experimentation, it is not clear
what the right answer is, but without historical data, they would never have
known to ask the question.
A good data warehouse provides access to the information gleaned from
transactional data in a format that is much friendlier than the way it is stored
in the operational systems where the data originated. Ideally, data in the ware­
house has been gathered from many sources, cleaned, merged, tied to particu­
lar customers, and summarized in various useful ways. Reality often falls
short of this ideal, but the corporate data warehouse is still the most important
source of data for analytic customer relationship management.

The Role of Data Mining
The data warehouse provides the enterprise with a memory. But, memory is of
little use without intelligence. Intelligence allows us to comb through our mem­
ories, noticing patterns, devising rules, coming up with new ideas, figuring out
6 Chapter 1

the right questions, and making predictions about the future. This book
describes tools and techniques that add intelligence to the data warehouse.
These techniques help make it possible to exploit the vast mountains of data
generated by interactions with customers and prospects in order to get to know
them better.
Who is likely to remain a loyal customer and who is likely to jump ship?
What products should be marketed to which prospects? What determines
whether a person will respond to a certain offer? Which telemarketing script is
best for this call? Where should the next branch be located? What is the next
product or service this customer will want? Answers to questions like these lie
buried in corporate data. It takes powerful data mining tools to get at them.
The central idea of data mining for customer relationship management is
that data from the past contains information that will be useful in the future. It
works because customer behaviors captured in corporate data are not random,
but reflect the differing needs, preferences, propensities, and treatments of
customers. The goal of data mining is to find patterns in historical data that
shed light on those needs, preferences, and propensities. The task is made dif­
ficult by the fact that the patterns are not always strong, and the signals sent by
customers are noisy and confusing. Separating signal from noise”recognizing


. 7
( 137 .)