My Photo

Clicky

  • Clicky Web Analytics

Your email address:


Powered by FeedBlitz

« Old World vs. New World in a Digital World | Main | Giving Credit Where it’s Due – Comments and Follow-ups on Attribution »

TrackBack

TrackBack URL for this entry:
http://www.typepad.com/services/trackback/6a00d83454a6d169e201a3fd1f4b8e970b

Listed below are links to weblogs that reference Don’t Give Me No Stinking Credit : Re-thinking Digital Attribution:

Comments

OK so we're all screwed.

If they give an award for the most bleak article on analytics, this one's going to win.

We live in a world where 99% of sites have Google Analytics, and of those who do only 1% know how to use it. Maybe Amex and Schwab can ascend to the celestial realms and attempt the type of attribution you suggest, but what about the other 99%?

Is it possible for ordinary people to make incremental improvements to their attribution analysis and optimization efforts, and if so what might they do?

Good post!
To add my 2 cents, and forgive for being a bit geeky, but I don't think A/B testing alone is going to be what we need. The problem is really one of learning an optimal policy over a sequence of events. To solve we are going to need to couple together both experimentation (to explore the environment) along with some method to assign credit back to the previous state/action pairs.
This is similar to an adaptive dynamic programing problem. A conceptual (as well as empirical) way to frame the problem is as a Markov Decision Process. The objective of the analysis is then to find the optimal policy over all the possible channels/states by calculating the long term value of taking an action at a particular state. The solution is to select the highest value action at each state - this gives the optimal lift over the entire process.

1850: Half the money I spend on advertising is wasted, I just don't know which half.

2014: Half the money I spend on advertising is wasted, but "digital" analytics says it's all bringing in customers.

I eagerly await a post that describes how to implement these attribution suggestions in Google Analytics.

You have some pretty clever people working for you, so I imagine one of them could snap out a post like that in no time flat.

I'm surprised this hasn't already happened!

Bueller? Bueller?

I'm calling you out Gary! ;)

Or maybe Avinash is going to have to do it.

Ouch!

Nice article. Have peddled similar approaches in UK for a while. Customers seem to prefer a "solution" that settles disputes and budget allocation rather than address the task of greater understanding of attribution and it's difficulties.

Verify your Comment

Previewing your Comment

This is only a preview. Your comment has not yet been posted.

Working...
Your comment could not be posted. Error type:
Your comment has been saved. Comments are moderated and will not appear until approved by the author. Post another comment

The letters and numbers you entered did not match the image. Please try again.

As a final step before posting your comment, enter the letters and numbers you see in the image below. This prevents automated programs from posting comments.

Having trouble reading this image? View an alternate.

Working...

Post a comment

Comments are moderated, and will not appear until the author has approved them.