In causally dense, complex environments, the attribution problem has no intrinsic answer.

From Attribution in online marketing: a Big Data problem by Kaiser Fung.

Though he doesn't use the term, Fung is reporting on the work of Avinash Kaushik, exploring the limitations of root cause analysis in causally dense and complex environments. While this is in the context of marketing data, I think the conclusion is true of all social science. He is discussing the example of a marketer trying to establish a causative understanding between initial inquiry and final purchase with multitude of sequential and parallel steps in between.

The concept of "attribution" is to distribute credit among one or more of these prior interactions. Kaushik walks through a bunch of models that can be used to divide credit.

Kaushik then points out that analyzing the above figure (especially when it has thousands of other rows) is a waste of time: "There are too many paths, and you can't actually control the path that a potential customer can take."

***

While Kaushik dives into the mechanics, here are some high-level takeaways from his post:

•The attribution problem has no intrinsic answer. There is no single correct answer. Everything is subjective.
•Many decisions affect the attribution outcomes. e.g. which sources are credited and which are not, which positions in the path are privileged and which are not, the time window for eligiblility, what counts as an "action" and what doesn't. Different decisions lead to different attribution schemes.
•Having more data creates more complexity but does not reduce subjectivity. On the contrary, more data creates more levers resulting in more assumptions.