One of the great tragedies of the matchback/attribution era is a failure to understand how presented merchandise determines sales volume across channels.
Let's go back to Nordstrom, way back, in 2005. Remember 2005? Home values never dropped, it was the safest investment you could find. Good times!
At Nordstrom, we conducted a typical mail/holdout test on all catalog and email marketing efforts. You're executing mail/holdout tests on all catalog and email marketing efforts, right? Right? RIGHT?!
Anyway, we mailed co-op funded catalogs ... the vendor paid the freight, and got to advertise what they wanted in the catalog. We had numerous catalogs that did not have any mens merchandise in them ... mostly womens merchandise was featured.
A funny thing happened. In nearly every test we analyzed, a significant amount of lift was sourced from mens merchandise ... merchandise not featured in the catalog. In other words, the catalog drove a customer online or to a store, where the customer (usually a woman) purchased merchandise for a man.
We didn't have to advertise mens merchandise to get customers to purchase mens merchandise.
Fast forward to 2013, eight full years later. I can count on one hand the number of email marketers and catalog marketers who perform this analysis.
You cannot identify this finding (womens pages drive mens demand) by doing matchback or by performing attribution work. Both methodologies fail miserably at telling you what the customer purchases, based on what was offered in your email or catalog marketing activities.
Give this analysis a try - it's terribly easy to perform. You'll be surprised by what you learn!!
Ok, let's look at a practical example of Primary / Secondary / Tertiary categorization of merchandise categories. In this case, we ...
Look at the first four rows of our life table (values of 0/1/2/3). These are the first 12-15 weeks after a customer buys for the firs...
We spent the past two weeks talking about the events and influences that shaped what I call "The Great Eight". My Influence...
If you don't like geeky math, please skip this post, because I am about to show you how the sausage is made! I have eight variables in...