TARGETING USERS BASED ON PREVIOUS ADVERTISING CAMPAIGNS

摘要

During a targeting technique, a machine-learning model is generated based on information about previous advertising campaigns and attributes in profiles of users of a social network (which facilitates interactions among the users). The information about the previous advertising campaigns includes specified target groups and associated feedback metrics obtained from individuals, such as impressions served, clicks and/or conversions. This machine-learning model is then used to calculate scores for the users based on attributes in their profiles and/or user behaviors (such as online activities) that indicate probabilities of their responding to a future advertising campaign for a target group. Moreover, based on the calculated scores, a subset of the users is associated with the target group. For example, the users may be ranked based on their calculated scores, and the subset may be those users having scores exceeding a threshold or a predefined value.

主权项

1. A computer-system-implemented method for associating a subset of users of a social network with a target group, the method comprising:
accessing information about previous advertising campaigns, wherein the information for a given previous advertising campaign specifies a target group and one or more associated feedback metrics obtained from individuals; using the computer system, generating a machine-learning model based on the accessed information and attributes in profiles of the users of the social network, wherein the social network facilitates interactions among the users; calculating scores for the users indicating probabilities of their responding to a future advertising campaign for the target group based on the machine-learning model and the attributes in the profiles of the users; and associating the subset of the users with the target group based on the calculated scores.