This is a reminder that there are just nineteen days left to provide your answer in The MineThatData Measuring Advertising Effectiveness Challenge. This is an exercise to help the multichannel retailing industry measure the impact of catalogs, postcards and e-mails simultaneously delivered to various customer audiences. This link has been the most visited link on this blog. I already have one solution, and am looking forward to more by the 1/31/2007 deadline.
Helping CEOs Understand How Customers Interact With Advertising, Products, Brands, and Channels
January 12, 2007
Please Help Our Industry Measure Advertising Effectiveness: 19 Days To Go
Subscribe to: Post Comments (Atom)
As usual, my summer schedule will dial back just a bit ... maybe three posts per week instead of five, sometimes four, sometimes more. And y...
It is time to find a few smart individuals in the world of e-mail analytics and data mining! And honestly, what follows is a dataset that y...
Sometimes you think "people already know this stuff". Sometimes you realize that Google Analytics give smart analysts almost no op...
If you want to understand why clients don't trust vendors and trade journalists, read this little peach from a week ago: Direct Mail is ...
"Albert, we have this issue with Newton's absolute time and space assumptions, we think it might be, well, a little bit off. Can you come up with a theory anyone with no grasp of complex physics or math can understand? And oh yeah, it has to fit on like a Powerpoint slide. And maybe summed up in one small table or something. Doable?"ReplyDelete
You're assuming that this exercise is as challenging as physics. This is just marketing analysis, no right or wrong answer, just an opportunity to try different methodologies.ReplyDelete
I wasn't comparing physics to marketing in terms of complexity - just that you're framing the answer before you know what the answer is. The relatively example was just an extreme to make the point. One of the biggest problems with marketers is that they are always framing the answers when they should be asking more intelligent questions.ReplyDelete
Maybe I have not clearly explained the problem. I created the dataset, so I know the exact answer to the problem.ReplyDelete
That being said, nobody else knows the algorithm I used, so I want for people to share their methodologies, and have an open discussion.
You mentioned that marketers always frame answers when they should ask more intelligent questions. Is this the case with every single marketer?
Might you be willing to share your name and profession with my readers, so they understand the context behind your comments?
My name is Paul and I work as a consultant in the Marketing/Ad world. To be honest Kevin, I came across your blog pretty much by accident and was having a philosophical moment. Let me explain a bit further why I left the comment.ReplyDelete
Firstly, I have no problem with your competition. I think it's a great thing to try and do if you want a debate about media channel and sales allocation. My approach would be some type of multivariate model - but I haven't looked very closely at the data so I can't be sure.
The single thing I took issue with was your framing of the answer and it sparked the thought (and for the record, no, I wasn't aware that you already had the answer - that wasn't very clear from your post, or perhaps I missed something).
Taking the thought to an extreme, you have the above problem - would we really know anything more about time and space if Einstein had to fit relativity on a PP slide? When Marketers want a 2 paragraph and one chart explanation to fit into a 15min board meeting slot, does the full picture ever get across? Sometimes, more often, not.
When it doesn't, it's because they spent too much time worrying about their simple answer than asking more intelligent questions. And no, this is not all Marketers - but enough, and generally the bad ones.
When you have a bunch of people running around to figure out an answer that looks like 'x', it pretty much precludes something that looks like 'y'. This may sound simple, but it's pretty much the biggest block to lateral thinking and innovative solutions there is. To get to 'y' you need people asking different questions, not thinking up new possible answers (that inevitably look like some variant of 'x').
Like I said, it's a more of a philosophical argument, and one I am sorry I hijacked your blog for. And it probably has little bearing on your competition as I misunderstood what you were doing to begin with.
But thanks for replying. I think I will add you to my reader!
You have nothing to apologize for, and you haven't hijacked anything.ReplyDelete
We enjoy a debate here. I wish more people would debate things.
I'm thankful you chose to leave your thoughts.