Thanks for pointing out that my figures were misleading (or, more to the point … that I failed to qualify them properly). Looking back at the post now, I don’t think I could obfuscated the matter any worse :-(. What I said:

Their future sales and profit were 46% and 57% lower, respectively, than for ads run previously at the regular price (i.e. the LTV of this new group of customers was dramatically lower than existing ones);

Two words were conspicuously (and fatally missing), and I would have to come to precisely the same conclusion as you in this case. What I should have said was:

Their future sales and profit were on average 46% and 57% lower, respectively, than for ads run previously at the regular price (i.e. the LTV of this new group of customers was dramatically lower than existing ones).

In short, the future value of the ‘via discount acquired’ customer segment proved to be many-fold less than their normally priced counterparts. Not only did they order less frequently, when they did purchase their average order size (and profit) was significantly lower, too. It was also pointed out that repeat customers who responded to the discount promotion subsequently reordered at an 18% lower rate than those who did not.

// To avoid any further confusion I’ve edited the original post. Thanks again Dave!

First, I was preoccupied with a number of other things (in particular, selling my other software company so I could focus exclusively on Deltalytics) and completely neglected this blog for several months. I’m back on it, though, with renewed energy and a higher sense of purpose. Second, my blog’s spam filter didn’t behave as expected and these comments were held up in a queue I didn’t notice until now. Gee, I hate when that happens!

My responses to these much appreciated earlier comments follows –

(1) To David Raab who said “Other possible reason: people didn’t see what they wanted in the catalog and dropped the company from their list of places to consider buying from, not realizing the Web site would include additional products not shown in the catalog.”

– This is an interesting - and I think perfectly valid - twist on my original thought that .. ‘The catalog “soured” their opinion of the company Perhaps simply by receiving the catalog, the shopper no longer viewed the company as “a cool place {read website} to shop,” but instead is now seen as another one of those catalog deals, and, therefore, not worth bothering with.’ However, I’d be willing to bet that the catalog, at least in in this case, fairly represented the company’s product mix if not completely. // I’ll check with John Lenser to see and will report back.

(2) Nick Radcliffe provided an insightful perspective on negative retention effects and notes that he has observed this phenomenon many times in his consulting practice.

– Nick included a link to his excellent “Optimal Retention Strategies” article [ see http://stochasticsolutions.com/retention.html ] wherein he describes the mechanisms by which attempts to positively engage the customer can have the opposite effect, viz. defection. Sometimes, in fact, it’s best to leave happy customers alone (so as not to annoy them); likewise the unhappy ones (reminding them of their displeasure can elicit an undesirable behavioral reaction, e.g. realizing and deciding that they never want do business with you again). It’s a tougher and more delicate balancing act than is typically acknowledged. In short - and I believe Nick would agree - the risk of promotions depressing reorder rates (including, if not especially, retention efforts) can and should be mitigated whenever practical; but can never be eliminated entirely.

(3) Martin Davis said: “I believe that the main force causing decreased response rates discussed above results from the email campaigns that preceeded or ran concurrently with the catalog mailed. The email satisfied the demand for the offer for this customer group. CMC has noticed increased response rates when it blasted an email asking customers to “look out” for the upcoming catalog in their mail box. Also, I’d love to know how many sku’s these Lenser companies had. Currently, internet browsing does not come close to replicating the experience of flipping the pages of a paper base catalog.”

– I’m not sure I completely follow [a] even if Martin’s assumption - that email campaigns ran prior or current to the catalog drop - is correct. Even if the email(s) had some behavioral impact, this observation begs the question of why the catalog-mailed segment would have reordered at such a dramatically lower rate. Indeed, no what matter else may have been going on during the catalog group, we must presume that no bias existed between the two test panels. Here again is Lenser’s summary to refresh our memories ..

In a recent test we conducted with a client, we created two panels of 50,000 customers each, both groups acquired on the marketer’s e-commerce site within the past three months — neither had been mailed a catalog. One panel was mailed a 48-page catalog; the other was not mailed. Based on a later matchback to the mail files, the one-time buyers not mailed the catalog responded at 3.7 percent, while those mailed the catalog responded at 2.1 percent. Of the two-time-plus buyers, those not mailed a catalog responded at 8.5 percent; those mailed responded at 3.6 percent. Panels also were created for older buyers. For buyers who previously had purchased more than 13 months ago, those not mailed responded at 3.4 percent; those mailed responded at 2.8 percent. This isn’t a one-time test. We’ve repeated this test with several clients and seen similar results.

Even if these two panels were treated differently (a sophomoric mistake I don’t believe the Lenser people are likely to have made), we’re still left with the question of why the catalog-mailed group reordered at a significantly lower rate? Which brings us back to square one, viz. the puzzling observation that receiving the catalog “put off” these customer somehow. Back to Martin’s comment … I’m not surprised that a heads-up email advising customers to look for an upcoming catalog in the mailbox had a positive effect. This can create a positive anticipation and associated void in the customer’s mind (i.e. something to look forward to) which is fulfilled and relieved when the catalog arrives. All it takes is for some statistically meaningful number of customers to open the catalog, rather than tossing it immediately into the trash, to increase response rate.

CMC has noticed increased response rates when it blasted an email asking customers to “look out” for the upcoming catalog in their mail box. Also, I’d love to know how many sku’s these Lenser companies had. Currently, internet browsing does not come close to replicating the experience of flipping the pages of a paper base catalog.

In fact, I have worked with one client (who I can’t name, unfortunately) who uses control group and uplift modeling very systematically, and who claims that in almost every campaign he runs, the last one or two deciles (ranked by uplift, i.e. difference in treated purchase rate minus control purchase rate) show negative effects.

I think there are a set of reasons, and don’t really find it all that surprising. I think your first two reasons are big. A customer’s opinion of a company or a product can easily be changed (including for the worse) if a piece of marketing alters their image or perception of it. For example, if a customer thinks a particular mobile handset would be perfect for business, and receives a communication that shows kids fooling around swapping videos with it, that may make the handset suddenly seem less appropriate. Or more prosaically, if a mailing features a celebrity whom the client happens to hate, that could put him or her off.

Interestingly, there is one area here negative effects are even more prevalent, and that’s in retention activity, where attempted retention efforts often actually trigger defection. I’ve written about that at http://stochasticsolutions.com/retention.html.

Your point is well taken (that you have to look at the back-end), but in the example you give, the discounted offer is still better. Assume your control would have yielded 100 customers worth $100; then your discounted promotion would have yielded 400 customers worth $43 (i.e., 57% less). That’s a total value of $17,200 (400 x $43) for the discounted promotion vs. $10,000 (100 x $100) for the control. Which amount would you prefer in your bank account?

Of course, you could change your assumptions to yield a different result. Either way, it comes down to the same thing: you have to run the numbers.