Choosing an attribution approach that is right for you

Let me start this section by saying: there is no ‘right’ attribution model. There are no off-the-shelf solutions out there that you can buy, drop on your data, and hey presto: instant, accurate campaign evaluations.

In order to get to a view of campaign performance there are concessions you must make, the biggest being whether to split your views of the online and offline world in to independent, mutually exclusive existences, or whether to try and integrate them. No: I take that back. The biggest concession is how much time (or money) you’re willing to invest in improving your understanding of how your advertising works. More advanced techniques may take weeks to generate, and then need ongoing support and tweaks.

The underlying complexity driving this decision is a result of the vastly different data sets that arise from the offline and online worlds. The former are generally traditional media channels such as radio and TV, to which you may physically be unable respond in kind (at least until touchscreen TV technology and its ilk is widely deployed). Adverts are served at set times in the programming, and are ‘slow’ at typically 10-30seconds in duration. Whether an individual has seen your advert is an unknown.

Contrast this with online advertising where adverts are shown across most pages, at any time, are renewed with each refresh and sometimes with each scroll. A user browsing around may be exposed to tens or hundreds of adverts in a very short space in time, with every viewing and interaction tracked to the nth degree. Advert content (‘creative’) can be generated programmatically on the fly leading to a multitude of different versions and, significantly, there is (with some exceptions) a cookie record tracking the sequence of what you’ve seen and done.

In essence: you have offline data that needs (let’s say) weekly aggregations in order to provide sufficient sample volumes for a robust pattern to emerge. You then have online data that comes thick and fast, but where scale is thinned by high variety and fine detail.

So gives rise to two main techniques, Econometrics and Digital Attribution. And occasionally: an attempted mash of the two.

Econometrics attempts the holistic view, giving up some of the finer detail in order to give an all-encompassing view. Models will vary in complexity (often determined by the amount of time invested in developing the model), but the basic premise is one of linear relationships: do more of advertising type A, get a proportional increase in sales back x weeks later.

Digital Attribution foregoes explaining the offline activity and instead makes use of the online tracking technologies to try and piece together a customers’ journey. Broadly speaking, these techniques fall in to two camps. The first correlates customer interactions with sales activities, and leaves sales unexplained by patterns in the digital data in an unallocated ‘pot’. The second fully apportions the known sales across digital advertising channels. Both may choose (or not) to make sequencing and chronology a factor, but both techniques make use of case-wise customer journeys as opposed to ‘activity volumes’ as used in econometrics.

I’m not an econometrician, and my work falls in to this second set of techniques: digital attribution. In agencies this is often a complementary piece to an econometrics project, and is used to provide further, more granular insight in to the finer detail of online campaign performance.

So, having set up the background, let’s talk more about this latter field of analysis.

Attribution in the Media and Advertising Industry

I work as an agency analyst in the media and advertising sector, and by far the most commonly requested work is attribution analysis.

For the non-layman, this is the process of modelling which adverts have helped generate incremental business revenue, be that in the form of new customer interest as a precursor to sale or the sale itself, and then in some manner awarding nominal credit to that advert. The ratio between cost and credit is used to understand which strategies are generating the best return on investment for the next planning cycle.

An example then: let us imagine a customer who responded to seeing our TV advert by entering our brand name in to an internet search engine. Clicking on a resulting paid-for link they landed on our web site where they completed an order. Our customer also happened to have read a magazine in which one of our adverts had been placed, but it failed to resonate with them and they skipped over it.

Before bandying numbers and models around, it’s worth just remembering that the true purpose of attribution lies in answering these questions:

  • How do we know the customer saw the TV advert and responded to it?
  • How do we know the magazine advert failed to resonate?
  • What role did the search click play?
  • What was the relative importance of each advert to the sale, and ultimately, was it worth me spending the money on it?

I feel these basic concepts are often not given due appreciation in the rush to produce “a model” – merely having the latter seemingly more important than the question it is intended to answer.

Simply exposing a potential customer to an advert, for example, doesn’t mean it was effective. Likewise, how a customer navigates their web browser to your site might just be a route of convenience rather than via an opinion influencing step. And lastly; at what point does the customer journey cease to be influenced by advertising, and instead move over to being driven by the customer-service experience?

For an individual customer, these questions are admittedly impossible to answer. But across a larger sample size we can use data to identify repeat patterns between advertising and customer response. We can identify the channels that typically favour successful sales over missed ones. Crucially though, in the process of quantifying this influence we have to apply some assumptions about how we believe our customers respond. This is where the art mixes with the science: having strong insight in to your customer journey can really shape the solution for the better.