Google has officially announced the Data-Driven Attribution model that will replace Last-Click as it’s default attribution model in Google Ads. With increased user privacy policies enacted across today’s advertising landscape, their focus has shifted towards tools that both help marketers achieve their goals as well as put the end users first.
“One critical tool is machine learning, which can be used to fill the gaps in observed data and unlock new insights into consumer behavior. For example, conversion modeling powered by machine learning allows you to preserve measurement even when cookies or other identifiers aren’t present,” writes Vidhya Srinivasan, VP/GM Buying, Analytics and Measurement, at Google Ads.
“Data-driven attribution in Google Ads takes this a step further. It uses advanced machine learning to more accurately understand how each marketing touchpoint contributed to a conversion, all while respecting user privacy.”
How Does Data-Driven Attribution Work?
Google’s Data-Driven Attribution model uses conversion data to calculate the actual contribution of each ad interaction across the conversion path.
The difference between the data-driven model and last-click model is significant. As opposed to crediting only the most recent interaction for a conversion, data-driven attribution gives credit based on how people engage with your various ads along their path to becoming your customer.
The machine learning that powers this data utilizes several different traffic/conversion sources to properly allocate credit, including website, store visit, and Google Analytics conversions from Search (including Shopping), YouTube, and Display ads.
Are There Data Requirements To Be Eligible for Data-Driven Attribution?
Advertisers will need a certain amount of data present in their account otherwise the option to enable the Data-Driven Attribution model won’t show.
According to Google, “as a general guideline, for this model to be available, you must have at least 3,000 ad interactions in supported networks, and a conversion action must have at least 300 conversions within 30 days.”
Once you have the necessary data, Google’s system can begin to formulate the data-driven model for your account, and you will be able to see the results in Google Ads after you’ve had sufficient data for 30 consecutive days.
There are also requirements to continue tracking with this model after you have become eligible. Advertisers will need to maintain at least 2,000 ad interactions in supported networks or above 200 conversions with a conversion action(s) within 30 days.
Users will be alerted that their data is below the requirement, and if they aren’t able to meet the minimums the attribution model will be automatically switched to the Linear model.
Other Attribution Models Are Still Available
Although the Data-Driven model will be the default moving forward, all other options attribution options will remain available to choose from.
The other attribution models are:
- Last click: Gives all credit for the conversion to the last-clicked ad and corresponding keyword.
- First click: Gives all credit for the conversion to the first-clicked ad and corresponding keyword.
- Linear: Distributes the credit for the conversion equally across all ad interactions on the path.
- Time decay: Gives more credit to ad interactions that happened closer in time to the conversion. Credit is distributed using a 7-day half-life. In other words, an ad interaction 8 days before a conversion gets half as much credit as an ad interaction 1 day before a conversion.
- Position-based: Gives 40% of credit to both the first and last ad interactions and corresponding keywords, with the remaining 20% spread out across the other ad interactions on the path.