December 04, 2013


Attribution is terribly important these days, don't you think? From the inaccurate and simplistic matchbacks that revolutionized the catalog industry ten years ago to the multi-touch models that incorporate social/mobile activities, we're almost forced to employ some sort of Attribution model in our results analytics.

An Attribution model provides an estimate of the impact each advertising channel had on an order. If a customer purchased after touching catalog - email - email - social - affiliate, we don't want to give all credit to the catalog (matchbacks), or all credit to the affiliate (last touch). Both methods are wrong.

In fact, every Attribution methodology is wrong. And that's ok. We simply cannot crawl inside the head of a shopper in Upstate New York and divine exactly why a purchase happened. 

Everybody has to make a guess at some point, everybody has to infer just how effective each marketing channel is.

There is a piece of the Attribution puzzle that is missing. It's the forward-looking piece.

Attribution has a serious limitation. You look backwards, and you make a guess as to whether marketing activities were profitable or not. Not many folks "do the opposite" ... not many folks look forward, and estimate how the future of the business changes as you make changes to the advertising budget.

In upcoming weeks, we'll explore a "future" view of Attribution - combining the work of your favorite Attribution vendor with a five year estimate of demand/profit given different marketing investments.

Come along for the ride, ok?!