Google expands its AI use to detect invalid ad traffic

Google has introduced new measures to combat invalid traffic (IVT) in digital advertising, in collaboration with its Ad Traffic Quality team, Google Research and Google DeepMind. According to the company, the updated system uses large language models to more accurately detect ad placements associated with non-genuine activity.

Defining the Invalid traffic for advertisers on their platform, the company said, “Invalid traffic - ad activity that doesn’t come from a real person with genuine interest - wastes ad budgets and erodes trust. We’re using large language models to keep advertisers, publishers and users even safer on our platforms.”

The new applications analyse app and web content, ad placements and user interactions, resulting in a 40% reduction in IVT linked to deceptive or disruptive ad-serving practices. These measures aim to ensure that advertisers reach their intended audiences while removing policy violators from the platform.

Google continues to conduct automated and manual checks to prevent advertisers from being charged for invalid traffic, even if ads are served.