What is Marketing Attribution?
Marketing attribution, also called multi-touch attribution, is the identification of the user actions that contribute to a desired outcome, such as a purchase, and the assignment of a value to each.
Why does Marketing Attribution matter for marketers?
Budgets follow credit. How a business attributes a sale to channels decides which channels are funded, so a model that overstates one channel quietly moves money toward it.
Where does Marketing Attribution stand today?
Attribution depends on being able to follow people across touchpoints, and that has become harder: Apple's App Tracking Transparency (April 2021) required permission for cross-app tracking, and Google decided in July 2024 to keep third-party cookies in Chrome rather than remove them. Reference sources warn that attribution models often diverge from the lift measured in controlled experiments.
Common use cases
- Comparing the contribution of channels and campaigns
- Deciding where to move budget
- Checking model output against experiments
Wikipedia groups attribution models into four families. Single-source models give all the credit to one event, such as the last click, and are widely considered less accurate than the alternatives. Fractional models share credit across touchpoints by equal weights, time decay or other rules. Algorithmic (probabilistic) models use statistical modelling and machine learning to estimate the probability of conversion across touchpoints. Customer-driven models collect zero-party data, meaning information customers give directly.
Limits to keep in mind
The same source cites research showing that attribution models frequently diverge from lift measurements from controlled experiments, and that selection bias can make a model overstate touchpoints that merely happen to be seen by people who were already likely to buy. That is why attribution is often paired with experiments and with marketing mix modelling.