Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium for displaying digital components on client devices based on predicted user attributes of users are described. In one aspect, a method includes updating, at a client device of a user, a list of user group identifiers for the user to include a particular user group identifier that identifies a particular user group. A determination is made, for each user attribute of multiple user attributes, a score based on a quantity of user groups identified in the list of group identifiers for the user that include, as a membership attribute, the user attribute. A digital component request including data representing the list of user-group identifiers is sent to a content distribution system. Digital component data identifying a set of digital components selected based on the data of the digital component request is received.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for providing digital components to a client device. Methods can include assigning a temporary group identifier to a client device that identifies a particular group, from among a plurality different groups, that includes the client device based on a current period of user activity on the client device. A training set is generated for training a machine learning model that generates user characteristics. A request for digital component is received from the client device that includes the temporary group identifier currently assigned to the client device, a subset of activity features and one or more additional features that are based on the client device. The machine learning model generates one or more user characteristics based on which one or more digital components are selected and transmitted to the client device.