Abstract:
An online system matches a user across multiple online systems based on image data for the user (e.g., profile photo) regardless whether the image data is from the online system, a different but related online system or a third party system. For example, to match the user across a social networking system and INSTAGRAM™ system, the online system compares the similarity between images of the user from both systems in addition to similarity of textual information in the user profiles on both systems. The similarity of image data and the similarity of textual information associated with the user are used by the online system as indicators of matched user accounts belonging to the same user across both systems. The online system applies models trained using deep learning techniques to match a user across multiple online systems based on the image data and textual information associated with the user.
Abstract:
Embodiments include one or more client devices accessible by users, an online system, and one or more partner systems such that the online system is able to identify a user of the online system across different devices and browsers based on the user activity that occurs external to the online system. A user performs user actions (e.g. purchase a product) on a web page of a partner system and may provide personally identifiable information (PII) to the partner system. The partner system provides the hashed PII and user actions performed by the user to the online system. The online system identifies a user profile on the online system by matching personal information in the user profile to the hashed PII. The online system generates a confidence score indicating a likelihood that the identified user of the online system is the individual that performed the external user action.
Abstract:
A method is disclosed for attributing conversions among multiple members of a socially connected influence group, such as a household. Data from advertising impressions, including views and clicks, is maintained by an online system. When a conversion is made, the social network of the user creating the conversion event is analyzed. An influence group, defined as a group comprising the users and group of socially connected users whom influence the purchasing decisions of the first user, is created. Conversion data is analyzed for the first user and the other members of the influence group. This data is weighted to determine the propensities of successful conversions among all members of the influence group.
Abstract:
An online system tracks identities of users that interact with the online system. The online system sends a browser identifier for storing on a client device that interacts with the online system. The browser identifier uniquely identifies a browser of the client device used for interacting with the online system. A content provider system receives the browser identifier from the client device and uses the browser identifier for logging user actions associated with content provided by the content provider system. The content provider system sends user action logs to the online system and the online system determines users that used the client device at a timestamp associated with the user action log. The online system provides the user identifiers to the content provider system. The content provider system uses the user identifiers to generate reports.
Abstract:
An online system matches a user with a user of a third party system by comparing user identifying information maintained by the online system with user identifying information maintained by the third party system. To determine how accurately different types of user identifying information identify an online system user, types of user identifying information maintained by the online system are compared to types of user identifying information maintained by the third party system. A score is associated with various online system users based on the number of types of user identifying information associated with the user by the online system matching types of user identifying information associated with a third party system user. Based on the scores associated with different users, a measure of accuracy in identifying an online system user is determined for each type of user identifying information.
Abstract:
An online system receives information describing a target group of online system users from a third party system and determines whether to store the information describing the target group. Online system users included in the target group are identified and scores are determined for each of the identified user. A score associated with a user represents the online system's effectiveness in targeting content to the user via targeting criteria maintained by the online system. Based on the scores, the online system determines a group score associated with the target group and stores the information describing the target group if the group score satisfies one or more criteria. If the information describing the target group is stored, the online system may determine whether to continue storing the information describing the target group based on revenue obtained by the online system from presenting content based on the target group.
Abstract:
An online system maintains an identity graph having links between different types of user identifying information (e.g., email addresses, phone numbers, user identifiers) describing various users of the online system. Based on information received from various sources describing relationships between different types of user identifying information describing a user, the online system generates confidence values for each link between different types of user identifying information. In some embodiments, a confidence value accounts for an amount of time since information describing a relationship between different types of user identifying information was received from a source. If the confidence value of a link between different types of user identifying information equals or exceeds a threshold value, the online system determines the different types of user identifying information are correlated with each other, allowing the online system to correlate user identifying information without storing user identifying information received from sources.
Abstract:
A server system receives, from a first device, a request to authenticate a user with a third-party application using a social networking system and contact information of the user. The server system requests the social networking system to authenticate the user based on the contact information. The social networking system is different from the third-party application.
Abstract:
Online system users interact with one or more third party systems, with the online system maintaining an account for each of its users and each third party system maintaining a third party account for each of its users. The online system compares information in a user's account to accessible information in third party accounts and establishes connections between the user's account and o third party accounts based on the comparisons. A connection between the user's account and a third party account includes a confidence level indicating a likelihood of the third party account being associated with the user of the online system corresponding to the account. A third party system may request information from the online system about a user specifying a threshold confidence level, allowing the online system to return information from third party accounts having connections to the user's account with at least the threshold confidence level.
Abstract:
An online system receives a request from an online system user to present a content item associated with an action that may be performed on a third party website not associated with the user. The online system identifies a set of third party websites on which the action may be performed based on information provided by content publishers associated with the websites describing performances of the action on the websites. The online system predicts a likelihood a viewing user of the online system presented with the content item will perform the action on each third party website based on the information provided by the content publishers and selects a website associated with a highest predicted likelihood the viewing user will perform the action on the website. The online system generates the content item including a link to the selected website and provides the content item for presentation.