Attention application user classification privacy
Classification of the user of an attention application is moved from the cloud, where the classification is performed by advertisers based on trackers that follow a user, to the attention application itself. A user of the attention application controls inputs to the classification model and can exclude sensitive privacy information from inclusion in the classification model. The classification model is applied locally at the attention application to a catalog of advertisements and without revealing to trackers and advertisers whether attention was paid to particular ads. An analytics provider may have increased access to attention applications and can form ad campaigns and provide performance data thereon to advertisers without infringing attention user privacy. The system directs value away from trackers and advertisers and to attention application users and publishers.
1. An attention application advertisement delivery system, the system comprising:
a device that includes at least one hardware device processor; and
a computer readable storage medium storing instructions for execution by the at least one hardware device processor, the instructions, when executed, causing one or more of the at least one hardware device processor to:
receive, from an analytics consumer based at least in part on ads of an ad catalog being serviced to users of a target market via an attention application that locally performs ad matching and user classification, a request for attention analytics on the target market, wherein each ad of the ad catalog hides, from the analytics consumer, respective identities of the users that view the ads on respective attention applications;
receive, from one or more attention applications associated with the users of the target market and via a zero-knowledge proof that hides an attention metric input for a particular user, attention analytics associated with respective users associated with one or more attention applications, wherein receiving the attention analytics via the zero-knowledge proof comprises:
receiving a blinded token from a pool of blinded tokens, wherein the blinded token includes a cryptographic key present in the ad catalog; and
wherein the attention metric input hidden by the zero-knowledge proof is indicative of attention paid, by the particular user, to ads matched and serviced locally by the attention application;
determine, using the attention analytics received via the zero-knowledge proof, attention analytics of the target market with respect to at least one ad in the ad catalog; and
transmit the attention analytics of the target market via a shared ledger, wherein the attention analytics of the target market are accessible by the analytics consumer via the shared ledger using an analytics key.
2. The system of claim 1 , wherein the analytics consumer pays users of the attention applications a digital asset for attention paid to the at least one ad in the ad catalog.
3. The system of claim 1 , further comprising:
determining a success metric of the at least one ad in the ad catalog, the success metric being based at least in part on an amount of a digital asset paid per attention unit to the at least one ad in the ad catalog.
4. The system of claim 3 , wherein the success metric is further based at least in part on a size of the target market.