Attention is measured as users view ads and content in the browser’s active tab in real time. The Attention Value for the ad will be calculated based on incremental duration and pixels in view in proportion to relevant content, prior to any direct engagement with the ad. We will define further anonymous cost-per-action models as the system develops. Ads are then anonymously matched with customer interests using local machine learning algorithms. This means less irrelevant ads. Brave will work with publishers and advertisers to establish best practices for judging user attention. One potential metric: the number of total views of advertising content for a certain number of seconds. Or, points assigned on the length of a view.
