Background
Throughout our Big English banner pre-testing in FY2425, we've observed an extreme increase in impressions served for some banner types in some geographies; notably desktop large in the U.S.
Concurrently, Product Analytics have been observing increases in page views and/or unique devices in the U.S. and other markets. They believe bots and automated traffic are responsible for some significant portion of those increases, and we believe that same automated traffic is bloating our banner impression data.
Planned action
The suggestion from Product and backed by Fundraising is to exclude traffic from IPs generating an abnormally high number of banner impressions in our internal impression reporting.
Considerations
- What threshold should we use? Elliott observed that in a recent Big English pre-test, 5% of impressions served came from IPs with more than 10 hits.
- How will we report on the impact? Can we model a given approach with recent data before implementing it? Can we roll the change back after it is made?