Jim answers questions from fellow Drillers
(More questions with answers here, Work Overview here, Index of concepts here)

6033% ROI
—————-

Q: We have exchanged email a few times, and I don’t recall if I ever said thank you for your book.  While I had been experimenting with many CRM programs in my little dry cleaning shop, your book gave my thoughts order and clarity to refine what I had started.  Today, I see the world differently.

A: Well, thanks for the thanks!

Q: You may or may not remember me. Just after I sold my dry cleaning shop, I had bought your Drilling Down book. I was the dry cleaner who had been doing rudimentary data mining and CRM with a point of sale system I had developed in Regina, Saskatchewan.

A: I do remember. Internally, I was thinking, “Wow, this is going to be a real test of the Drilling Down concept”? I mean, I have seen it work in many small businesses, but dry clean (seems to me) is a very tough, tough business. Too many players, a lot of competing on price, etc. A great environment for underground customer marketing in terms of beating the other guy – they will never know what happened to them. But still, tough for small owner / operator to have the “will” and time to really make it happen. So yea, I remember…

Q: Well, I’ve continued working within the dry cleaning as a marketing consultant. The programs I had developed in my shop have now been transplanted into a few of my client’s shops, and are bearing fruit.

Tonight one of my clients reported a ROI of 6033% doing direct mail to certain customers in his market in California. Another client of mine reported his fourth year of steady growth. One of my first clients has been showing a 7 percent annual compound growth, and he is in a flat or declining market. What began in my shop has been proven across North America, into Europe and Australia by my clients.

A: I can’t express how exciting that is. Congratulations!

Q: Jim, data mining dry cleaner’s data is a blast. You would be stunned at the quantity, and quality of data a dry cleaner gathers today. Would you ever have thought data mining could be applied to suits and shirts? Well yes, it can.

A: I am stunned, and I bow to your most excellent Drilling!

Q: Once again, thank you.

A: And thank you for sharing this, it’s very, very exciting to hear. Like you said, no other word for it than “stunning”. I remain most stunned!  Keep me informed. Perhaps you should write a book?

Jim

Defining Churn
———————

Q: I work for an economics consulting firm based in Washington DC. I am researching customer churn and customer displacement statistics across a variety of industries to try to establish a benchmark of what is considered high and low customer displacement.

A: Nice to meet you, and a noble task!

Q: Do you happen to have any such churn statistics, or know if a place you could recommend?  I found plenty of statistics regarding churn rates within the telecom industry, but am most interested in companies that are involved in business-to-business relationships with their customers (relationship between a customer and a supplier).

In addition, I would also like to find churn statistics for customers who use multiple suppliers. For example, a customer may go to several grocery stores rather than sticking with one dedicated store.  I would be interested in learning more about the statistics companies in these types of industries use to track customer displacement.

A: The reason you find a lot of churn info in telco / cable is the end of the customer life is easily defined by the disconnect, and these numbers are reported publicly as part of annual reports and so forth. In many other businesses like the ones you describe, typically the companies have failed to define customer defection and so in their minds, there is no churn because there is no defection.

A “customer”, even though they have not contacted the company for 3, 5 or 10 years, is always still a customer. If the company thinks like this there is no churn rate to be measured, by the definition the company has chosen for itself.

At the same time, defining defection is pretty easy to do by looking at the transactional data and defining the patterns of defection, for example “if a customer has not ordered from us in 3 years they are highly unlikely to order again”. That’s defection defined; you just put a line in the sand and say “3 years no contact is a defection”. The company then should declare customers in this status “defected” and then a churn rate could be found. This is pretty easy to do, so if not executed, one of two situations exist: either the company does not have the data or they don’t have the “will” to discuss, internally or externally, the concept of customer defection.

A third possibility exists: the company in fact has the data and has defined defection, but would never, ever speak to churn or customer defection in any kind of public forum because this information is so critically important from a competitive and strategy perspective. To discuss these numbers or the implications in public could have dramatic consequences for company positioning in the market or stock price. So if they have the numbers, they’re locked in a safe.

As a result, I’m sorry to say, I do not have any broad-based “sources” for you, save one possibility: a book called The Loyalty Effect by Frederick F. Reichheld (1996). In this book, Reichheld goes through the business models of 25 different companies that excel at retaining customers in different industries , and proves out the financial model of customer retention using real data. This is the book where the quote, “It costs 5x more to acquire a new customer than retain a current customer” (or the various bastardizations) came from. So it might help you out.

The only other thing I can suggest is that “churn” is not always the word used to describe these stats but is most often used when the disconnect is easily defined, as in telco / cable; “displacement” is a rare use for this idea as far as I can tell..

“Customer Turnover” is a popular phrase in Europe and is used by some in the US; also “defection rate” is used quite a bit. So if you’re pounding on Google to try to find these numbers, try those phrases and others you may find when doing these searches. Banking / finance / insurance is another area where the “disconnect” is often easily defined, so you will find various defection rates in some of their case studies on the web.

Jim

Get the book at Booklocker.com

Find Out Specifically What is in the Book

Learn Customer Marketing Concepts and Metrics (site article list)

Download the first 9 chapters of the Drilling Down book: PDF 

Jim answers questions from fellow Drillers
(More questions with answers here, Work Overview here, Index of concepts here)

Please note: The business discussed below is a “continuity business”, where customers consume the product and need to either reorder from the company every few months or seek alternatives sources for the product. In this scenario, the behavior of customers is generally governed by the Latency Metric.

Q: Currently we mail our current customers direct mail every 6.5 weeks.  We have a new VP and he is asking if that is the optimal spacing of mailings.  I’m wondering if there are any best practices for setting up frequency tests?  If you can shed any light on how to set up such a test I would greatly appreciate it.

A: Well, do you know how you got to the 6.5 weeks number in the first place?  Somebody must have thought it was a good idea based on some kind of data (I hope)!

Obviously, there is some significant financial risk in simply “moving the drop around” and testing results that way.  You can do it, often by slivering off parts of the drop and dropping then at different times, but there could be a substantial financial penalty for approaching the problem this way – both on the cost and sales sides.  This is especially true when you have a current schedule that seems to be working.

The first thing I would do, if possible, before taking on the risk of messing with the mailing is to see if you can find any segmentation /  frequency that makes more sense from the customer data itself.  Since you also have a web site, there probably is evidence of “natural purchase cycles” the customer engages in that operate outside the mail drop – customers ordering “when and how they want to”.

Can you find evidence that the average purchase cycle is more like 5 weeks or 7 weeks?  How does this differ by product line, or packaging of the product?  Both segmentation by actual customer behavior and segmentation by product line will generally provide increased profits, provided the cost of dropping different mail streams does not overpower the increased sales.

For example, if someone can buy a “90-day supply”, well, 6.5 weeks is a bit  early for the mailing, I’d think.  If they can only buy a 30-day supply, well, it seems to me that 6.5 weeks could be a bit late.  Look to actual  purchase cycles by product line / supply length and see if you can find any patterns in the purchase behavior.

The key to this kind of analysis is to line up all the customers so that the purchase cycles match.  In other words, you need to enforce the same start date.  One way to do this, for example, is look at all new customers who started in January 2007; of the ones that bought again, when did they purchase – 5 weeks, 6 weeks, 7 weeks out?  What percentage of new starts in January (or any other month) purchased in each of the subsequent weeks?  Be aware choosing a single month may create results that have a seasonal bias, but I’m not sure that is relevant in a product line like yours.

A more complex but possibly more accurate way to do this is to “normalize” the start date of all new customers in 2006 and then look at the subsequent purchase patterns – given the same start date, what percent bought again 5 weeks out, 6 weeks out, 7 weeks out? You can achieve virtually the same thing by taking each month of current year and running it through the same drill as the one described above for following year, though it won’t be as accurate.

Once you have nailed the cycle for new customers, you can move on to see if  there is any change in optimal cycle date as customers age.  My guess is the cycle probably gradually lengthens until the customer defects.  If this is  true, it might be worth it to do two mailings with different cycles – one cycle for customers who became new customers in the past (say) 6 months and all other customers.  It’s likely in this business there could be an important behavioral difference between new and current customers that would allow you to deliver a more optimized mailing cycle.

Failing access to any analytical means to drill down into the data first, because either you lack the resources or simply don’t have the time, set up your next drop with flagged segments based on “weeks since last purchase” and look at profit per customer.  You could also back into this if you have good promotional history on your customers.

In other words, if you are going to drop “everybody” at the same time, there must be a segment where for this single drop, the time since last purchase based on arrival of the mail is 5 weeks ago, 6 weeks ago, 7 weeks ago, and so forth.  If you flag these segments before the drop in the database, you should be able to go back and determine sales per customer mailed for each segment.  This will tell you if your timing should be adjusted.  Further, you might divide these time-based segments, if there are enough members in the  segment, along various product lines.

Then, once you have a handle on the general cyclicality of different segments, you can get to profit per segment by using control groups to measure the lift and profit by segment.

A careful analysis of the next drop (or as I said, a previous drop if you have good history) should tell you which drop cycle for each product line is optimal.  From there, you have to look at economies of scale and decide if  you can afford that kind of segmentation.  You may find that due to the economies of scale in the mailing, you simply cannot drop 50% of your mail one week and the other 50% the next, for example.  But you might find enough support in your analysis to either justify the current 6.5 week drop as the most efficient, or to move it up or back somewhat.

Another way to approach the “timing problem” relative to economies of scale would be to try “reminder to re-order postcards” instead of mail or catalogs to some members of the group that require special timing considerations.  For example, new customers might not really need a catalog on their first drop, a postcard driving them to the phone or web site to reorder might be enough.

No silver bullets, I’m afraid. Just good ‘ol fashioned sloggin’ through the data ought to get you to where you want to go!

Jim

Get the book at Booklocker.com

Find Out Specifically What is in the Book

Learn Customer Marketing Concepts and Metrics (site article list)

Download the first 9 chapters of the Drilling Down book: PDF