Technologies used in the Yandex Advertising Network
Each day, millions of internet users view ads on Advertising Network sites.
To make ads more interesting to site visitors and more effective for advertisers and ad platforms, Yandex actively develops its own technologies:
- Data collection on users and pages. A substantial portion of the ads on Yandex Advertising Network sites are contextual ads that are displayed to users based on their particular interests and web page content. The individual interests of users are determined by their behavior when using Yandex services or their behavior on partner sites of the Advertising Network. The technology Crypta distinguishes social-demographic groups. Various user interests are accounted for when displaying behavioral advertisements. A page's theme is determined by the Yandex Advertising Network robot that regularly crawls the pages of sites on the Advertising Network.
- Effective targeting system. When selecting ads for display, we apply 15 types of targeting. These include 8 types of behavioral targeting (featuring auto-retargeting for all clients using Yandex Metrica), 6 types of contextual targeting, and audience targeting. The latter adapts to user interests across specific sites and regions, so it can predict future shifts in behavior, such as during holidays or other peak seasons. Owing to all the above targeting, suitable ads are selected for each user on each specific page.
- Predicting click probability. The selection of which ads to display on the Advertising Network is done automatically according to the maximum expected revenue. The machine-learning system MatrixNet is used to forecast click probability. It takes into account more than 120 ranking factors, which means that we select the ads that are most interesting to users and most profitable to our partners.
- Testing ad unit visibility. Advertising Network statistics only count ad impressions that actually allowed a user to have contact with the ad. In other words, for an ad impression, the ad unit must be at least partially in the user's field of view, and the contact time must be sufficient for the user to actually see the ad. Data on ad unit visibility is provided in the Yandex Advertising Network interface.
- Filtering invalid clicks. We employ a multi-factor technology that includes automatic and manual filtering methods to combat fraudulent or accidental clicks. Thanks to all this, our ad network enjoys the well-deserved trust of advertisers.
Learn more
- Yandex Advertising Network robot
- Behavioral targeting
- MatrixNet technology
- Testing ad unit viewability
- Advertiser protection
Contact support
You can also go to
Was the article helpful?
Previous