Drilling Down Home Page Turning Customer Data
into Profits with a Spreadsheet
The Guide to Maximizing Customer Marketing ROI

Site Map

Book Includes all tutorials and examples from this web site

Get the book!

Purchase Drilling Down Book

Customers Speak Up on Book & Site

About the Author

Workshops, Project Work: Retail Metrics & Reporting, High ROI
Customer Marketing

Marketing Productivity Blog

8 Customer
Promotion Tips


Customer Retention

Customer Loyalty

High ROI Customer Marketing: 3 Key Success Components

LifeTime Value and
True ROI of Ad Spend

Customer Profiling

Intro to Customer
Behavior Modeling

Customer Model:

Customer Model:

Customer Model:
Recent Repeaters

Customer Model:

Customer LifeCycles

LifeTime Value

Calculating ROI

Mapping Visitor

Measuring Retention
in Online Retailing

Measuring CRM ROI

CRM Analytics:
Micro vs. Macro

Pre-CRM Testing for
Marketing ROI

Behavior Profiling

See Customer
Behavior Maps

Favorite Drilling
Down Web Sites

About the Author

Book Contents

 Productivity Blog
  Simple CRM
 Customer Retention
 Relationship Marketing
 Customer Loyalty
 Retail Optimization
What is in the book?
  Visitor Conversion
  Visitor Quality
Guide to E-Metrics
  Customer Profiles
  Customer LifeCycles
  LifeTime Value
  Calculating ROI

  Recent Repeaters
  Retail Promotion
  Pre-CRM ROI Test
  Tracking CRM ROI
  Tutorial: Latency
  Tutorial: Recency
  Scoring Software
  About Jim

Customer Analysis: Auto Dealership
Drilling Down Newsletter #88  4/2008

Drilling Down - Turning Customer
Data into Profits with a Spreadsheet
Customer Valuation, Retention, 
Loyalty, Defection

Get the Drilling Down Book!

Prior Newsletters:

Hi Folks, Jim Novo here.

The auto dealership business is a complex one from a customer analysis perspective.  You have 3 or 4 separate businesses going on at the same time and each of them has a different natural cycle to them.  How do you start to unravel what is going on from a customer perspective and take action to "drive" increased profits?  That's the subject of the Driller Question this month.

Over on the blog it was Desirability month, kicked off by a Forrester conference on what "Engagement" really means to Marketing.  If you're interested in this topic, we cover both the Strategic and Tactical levels of the model.

For articles, we have Lester Wunderman weighing in on what Engagement means to Advertising, and Roy Young talking about how Silo Busting is good for Marketing.

A lot on the menu, let's get to that Drillin'...

Best Customer Marketing Articles

Ad Engagement & Silo Busting

Two article links on this page which stand by themselves and also compliment the Desirability Series on the blog (see below).  First, Lester Wunderman provides his view of what the concept of Engagement means to advertising.  Then, Roy Young talks about how to bust down Silos, a critical component of success to a customer-centric Strategy.

To access the full article review and links to the articles themselves, click here.

Sample Marketing Productivity Blog Posts

Forrester’s Marketing Forum this year covered Engagement, but not the kind of Engagement so often discussed in web analytics.  Nope, Engagement from a Marketing perspective, you know, surprise and delight leads to great customer experiences leads to better retention of customers and higher profits.

The first post includes links to the two keynotes.  I've spent a decent amount of time speaking with Brian Haven at Forrester about measuring and acting on Engagement from a Marketing perspective.  Brian puts forth a Strategic model and Kerry talks about Desirability - that which creates Engagement.

The next six posts outline a framework for understanding, measuring, and acting on the Desirability / Engagement model yourself.

To view this Series on Desirability, click here.

Questions from Fellow Drillers

Customer Analysis: Auto Dealership

Q:  First of all thanks for sharing your experiences in your blog / book.  I bought Drilling Down last week and I found it extremely useful, it’s easy to read and full of good advice for analyzing customer ROI and building models of performance.

A:  Thanks so much for the kind words!

Q:  After reading Chapter 16 –on how to score customers with a spreadsheet- I was asking myself how much data is enough to do a good RF score for a car maintenance business. 

A:  Hmmm... is a "car maintenance business" in Ecuador the same thing as a "garage" in the US?  What exactly is the business?  About how many customers do you have?  Can you buy a car at your business?  Or are cars just repaired there?  Is it a single location or chain operation with multiple units?  Do people come in for an oil change or is it just for mechanical trouble? Or are you just washing / cleaning cars?  I'm just trying to get a better picture of what we're talking about if you don't mind...

Q:  I'll give you some business facts:

· The company has two channels: car sales - new & used cars, and services - repair, maintenance and painting.  Each channel is managed almost as an independent business

· It's a chain operation with 4 units across the country, each unit has both channels.

· On the services channel, customers come to us seeking oil changes, brakes and engine maintenance.  We also do some serious mechanical repairs - crashed cars, broken engines, etc. and painting works.  We do not wash cars as a service.

· Yearly we pick around 1200 service orders on 850 customers, coming from a base of about 2000 different customers since we started the business in 2005.

A:  Impressive customer knowledge!  Somebody has been reading a book on this...

OK, I think we have enough to start!  First, if you have not already, read this piece, it deals with the oil change business in particular and the dealership business model in general.

Now to the questions:

Q:  Do you think a year of data can give us some results with a certain degree of confidence?  If the answer is no, then how much data do you think we need in order to achieve some good results?

A:  You probably have enough data, but this is a complex, hybrid model because it actually involves at least 3 or 4 businesses, so you'll need some "hybrid" thinking.  You clearly have some repeating behavior and what you really need to understand first is what that behavior consists of.  Let the data tell you the story.

The first thing I would do is try to understand these repeating segments.  Prediction really works best when the segments are clear and differentiated (see oil change piece above).

So, for example, you have probably at least these important businesses:

1. Vehicle purchase
2. Mechanical service
3. Oil change

These categories are different because the demand cycles are different:

1. Buying vehicle is almost like a 1x purchase, though you hope they come back, of course.

2. Mechanical service is an "on demand" thing, very hard to predict.

3.  Oil change is (supposed to be) a routine thing, should be easy to predict at least the *need* for an oil change.  Whether it happens or not is another story.  Also, If you take everybody who has had any oil change, that is also probably the largest group of customers.

So, if you are looking for segments, you probably find they look something like this:

1. Bought a vehicle, also gets mechanical service, and oil change

2. No vehicle purchase, but gets mechanical service and oil change

3. No vehicle purchase, no mechanical service, but gets an oil change

Given these segments, a few of the questions you might ask would be:

1. Of people who get an oil change, why do they stop with oil change / not repeat?

2. Of people who get an oil change, why don't they get mechanical?

3. Of people who get an oil change and mechanical, why don't they buy a vehicle?

Is their some common Action prior to them stopping that may have caused them to stop?  A certain kind of repair?  Buying a certain kind of car?  Waiting a very long time past when they were due for an oil change?

I'm not saying this is the data you will find, though it seems like a good guess.

What I am saying is the place to start all this is with a behavioral segmentation, and then asking the question, Why do they behave like this?  Is it pricing, business practices, customer service issues, scheduling, etc.?  Try to answer the questions raised by the behavior first.

Then, you have some basis to think about scoring / marketing.  Otherwise, you're just wandering around in the wilderness.  You have to start with a base, understand what the data tells you about customer behavior first.

My bold-faced guess is that the oil change business has the most total volume, and is most likely to repeat.  So what you want to do is upsell into mechanical and then when you have an oil and mechanical customer, upsell into vehicle purchase.

So, for a marketing example, when you do an oil change, you check a few common maintenance things and say, "Hey, did you know you will need brake pads pretty soon? Would you like us to do that when you come in for the next oil change?  If you get the brake pads when you come in for the oil, we'll give you a 20% discount on the labor".

That kind of thing.  If you were going to actively market this, you would send a reminder for the oil change when it's coming due, and in the reminder say "Remember, we offered you 20% off the labor if you get those brake pads changed".

Likewise, when they're now into both oil and mechanical (they are buying 2 products from you), you talk about buying a vehicle, usually based on a major mechanical problem of some kind.  "Since you get a lot of service here, we'll give you a deal on a vehicle".

It's a long, somewhat unpredictable cycle - except for the oil.  So you use the oil as a "base" and try to grow people into repeats up from there.  The only thing you really try to predict is "time for an oil change" and the rest is marketing, because the mechanical and vehicle purchase are fairly unpredictable.

If you are running something like the LifeCycle Grids to map customers, you would probably want to have a grid for each type of customer, segments 1, 2, 3 above.  The goal would be to migrate customers up into the higher value, multi-product line maps.

Q:  Another question I had after reading the Life Cycles chapter was: which kind of measuring does a better job?  Scoring through a fixed interval of data - picking the last 15 months of sales - or scoring through some kind of data continuum - 15 months of data this month, 16 months the coming month and so on?  Personally, I'd choose a fixed interval with enough data, but some people tell me this would tag some returning customers as new customers, which would be imprecise.

A:  I'd have to agree with "some people".

In this kind of business, which is a long-cycle, relationship business, I would use "Life to Date" sales to build the LifeCycle Grids, the "15 months of data this month, 16 months the coming month" idea.  It's the same as the example in the book, where the last column is "18+ months."  I wouldn't cut it off, unless perhaps at 5 years or so, when it is clear the customer is not coming back to by a vehicle.  Or maybe 10 years.

You want the time frame to match up with the cycle of the longest product plus another 20% or so in terms of time, so you catch any behavior lagging the averages.

Now, some of the decisions surrounding these ideas you will have to make based on your internal knowledge of the business.  If there is really not much profit in vehicle sales, or the volume is so low that it's only (say) 10% of profits, then it might not be worth your time focusing on.  You focus on profiling the oil and the mechanical, and the vehicle sales come when they come because you deliver a great customer experience and they trust you.

Q:  Thanks for your help, your words helped me to get a fresh perspective of the analysis I need to do.  By the way, your book is the most practical thing in data analysis I've seen in years.  Keep giving us your valuable insights!

A:  Thanks, you are most welcome, and I intend to.  Hope this has helped you decide on how to approach the marketing challenge!


If you are a consultant, agency, or software developer with clients needing action-oriented customer intelligence or High ROI Customer
Marketing program designs, click here

That's it for this month's edition of the Drilling Down newsletter.  If you like the newsletter, please forward it to a friend!  Subscription instructions are top and bottom of this page.

Any comments on the newsletter (it's too long, too short, topic suggestions, etc.) please send them right along to me, along with any other questions on customer Valuation, Retention, Loyalty, and Defection here.

'Til next time, keep Drilling Down!

- Jim Novo

Copyright 2008, The Drilling Down Project by Jim Novo.  All rights reserved.  You are free to use material from this newsletter in whole or in part as long as you include complete credits, including live web site link and e-mail link.  Please tell me where the material will appear. 


    Home Page

Thanks for visiting the original Drilling Down web site!

The advice and discussion continue on the Marketing Productivity Blog
Twitter: @jimnovo

Read the first 9 chapters of the Drilling Down book: download PDF

Purchase Book



Slow connection?  Same content, less graphics, think Jakob Nielsen in Arial - Go to faster loading website

Contact me (Jim Novo) for questions or problems with anything on this web site.  

The Drilling Down Project.  All rights reserved, all media.



Ask Jim a Question


Get the book with Free scoring software at Booklocker.com

Find Out Specifically What is in the Book

Learn Customer Marketing Concepts and Metrics (site article list)


This is the original Drilling Down web site; the advice and discussion continue on the Marketing Productivity Blog and Twitter.

Download the first 9 chapters of the Drilling Down book here: PDF
Purchase Book          Consulting