Framework for evaluating targeting models

    公开(公告)号:US10127573B2

    公开(公告)日:2018-11-13

    申请号:US14940794

    申请日:2015-11-13

    Applicant: Facebook, Inc

    Abstract: An online system predicts, using a first targeting model, a first group of users as candidates to be in a targeting cluster, and predicts, using a second targeting model, a second group of users as candidates to be in the targeting cluster. The online system determines a first set of users that are not part of the first group of users, and a second set of users that are not part of the second group of users, and provides surveys to the first and second set of users. The online system determines a first subgroup of the first group of users and a second subgroup of the second group of users, and provides an ad preferences tool to the first subgroup and the second subgroup. The online system scores the first and second targeting models based in part on responses to the surveys and/or the ad preferences tools.

    Framework for evaluating targeting models

    公开(公告)号:US10937053B1

    公开(公告)日:2021-03-02

    申请号:US16158309

    申请日:2018-10-12

    Applicant: Facebook, Inc.

    Abstract: An online system predicts, using a first targeting model, a first group of users as candidates to be in a targeting cluster, and predicts, using a second targeting model, a second group of users as candidates to be in the targeting cluster. The online system determines a first set of users that are not part of the first group of users, and a second set of users that are not part of the second group of users, and provides surveys to the first and second set of users. The online system determines a first subgroup of the first group of users and a second subgroup of the second group of users, and provides an ad preferences tool to the first subgroup and the second subgroup. The online system scores the first and second targeting models based in part on responses to the surveys and/or the ad preferences tools.

    DETERMINING A PRIMARY USER OF A CLIENT DEVICE AND PROPAGATING SETTINGS OF THE PRIMARY USER FROM THE CLIENT DEVICE TO AN ONLINE SYSTEM

    公开(公告)号:US20180115631A1

    公开(公告)日:2018-04-26

    申请号:US15299296

    申请日:2016-10-20

    Applicant: Facebook, Inc.

    Abstract: An online system propagates settings from a user's client device to the online system itself for the user. If multiple users of the online system use the client device, the online system propagates settings of a primary user of the client device to the online system, but does not propagate settings of other users of the client device to the online system. The online system logs accesses to the online system each day from the client device of each user. A user having a maximum number of logged days accessing the system and accessing the online system for at least 50% of the logged days is determined to be the primary user by the online system. The online system may use determination that a user is a primary user of the client device for associating actions with the user, selecting content for the user, and identifying the user.

    FRAMEWORK FOR EVALUATING TARGETING MODELS
    4.
    发明申请

    公开(公告)号:US20170140416A1

    公开(公告)日:2017-05-18

    申请号:US14940794

    申请日:2015-11-13

    Applicant: Facebook, Inc

    CPC classification number: G06Q30/0243 G06Q30/0245 G06Q30/0255 G06Q30/0277

    Abstract: An online system predicts, using a first targeting model, a first group of users as candidates to be in a targeting cluster, and predicts, using a second targeting model, a second group of users as candidates to be in the targeting cluster. The online system determines a first set of users that are not part of the first group of users, and a second set of users that are not part of the second group of users, and provides surveys to the first and second set of users. The online system determines a first subgroup of the first group of users and a second subgroup of the second group of users, and provides an ad preferences tool to the first subgroup and the second subgroup. The online system scores the first and second targeting models based in part on responses to the surveys and/or the ad preferences tools.

    Determining a primary user of a client device and propagating settings of the primary user from the client device to an online system

    公开(公告)号:US10523780B2

    公开(公告)日:2019-12-31

    申请号:US15299296

    申请日:2016-10-20

    Applicant: Facebook, Inc.

    Abstract: An online system propagates settings from a user's client device to the online system itself for the user. If multiple users of the online system use the client device, the online system propagates settings of a primary user of the client device to the online system, but does not propagate settings of other users of the client device to the online system. The online system logs accesses to the online system each day from the client device of each user. A user having a maximum number of logged days accessing the system and accessing the online system for at least 50% of the logged days is determined to be the primary user by the online system. The online system may use determination that a user is a primary user of the client device for associating actions with the user, selecting content for the user, and identifying the user.

    RESTRICTING TARGETED ADVERTISING ACROSS MULTIPLE ENVIRONMENTS

    公开(公告)号:US20170091815A1

    公开(公告)日:2017-03-30

    申请号:US14868136

    申请日:2015-09-28

    Applicant: Facebook, Inc.

    CPC classification number: G06Q30/0255 G06Q30/0257

    Abstract: A user makes a request to restrict targeted advertising through third party services accessed on a client device. A publishing system obtains information indicating that the user requested to restrict targeted advertising. The publishing system updates a profile associated with an account of the user to indicate that the user has requested to restrict targeted advertising. Based on the update to the profile, when the user communicates with the publishing system through the same or a different client device, the publishing system is restricted as to the information that can be collected and used for targeted advertising

Patent Agency Ranking