User identification system

A system comprising:

• at least one processor;
• and
• at least one non-transitory computer-readable storage medium storing instructions that, when executed by the at least one processor, cause the system to:
• generate, by a universal measurement identification system comprising one or more server devices, a ground truth data set comprising, for each of a plurality of known users, one or more data elements that correspond to user identification information or actions of each of the plurality of known users;
• provide, to each of a plurality of digital content providers, the one or more data elements of the plurality of known users from the ground truth data set;
• receive, from each of the plurality of digital content providers, predicted user identities for each of the plurality of known users based on the provided one or more data elements;
• generate a prediction accuracy score for each of the plurality of digital content providers by comparing the predicted user identities from the plurality of digital content providers to the ground truth data set;
• and
• based on the generated prediction accuracy scores for each of the plurality of digital content providers, generate an identity resolution model to predict user identities for unknown users based on predicted user identities received from the plurality of digital content providers.

A non-transitory computer readable medium storing instructions thereon that, when executed by at least one processor, cause a computer device to:

• generate, by a universal measurement identification system comprising one or more server devices, a ground truth data set comprising, for each of a plurality of known users, one or more data elements that correspond to user identification information or actions of each of the plurality of known users;
• provide, to each of a plurality of digital content providers, the one or more data elements of each of the plurality of known users from the ground truth data set;
• receive, from each of the plurality of digital content providers, predicted user identities for each of the plurality of known users based on the provided one or more data elements;
• generate a prediction accuracy score for each of the plurality of digital content providers by comparing the predicted user identities from the plurality of digital content providers to the ground truth data set;
• and
• based on the generated prediction accuracy scores for each of the plurality of digital content providers, generate an identity resolution model to predict user identities for unknown users based on predicted user identities received from the plurality of digital content providers.