Abstract: Methods, systems, and storage media for assigning multiple identifiers to user accounts are disclosed. Exemplary implementations may: receive an indication of an event; associate the event with a user; associate the user with at least a first account identifier of a plurality of accounts of the user; associate the user with at least a second account identifier of the plurality of accounts of the user, the second account identifier different than the first account identifier; add at least one of the first account identifier or the second account identifier to a custom audience relating to the event; target the custom audience through directed advertising; and deliver advertisements to the custom audience.

Abstract: An online system receives content items from content providers and delivers the content items to client devices of users. The online system receives a weight associated with an item described in the content item. The online system determines a rate at which a content item is delivered to users based on the received weight associated with the item and a rate at which users interact with the content item. The online system delivers the content item to users at the rate determined based on the received weight and the rate at which users interact with the content item. The online system may periodically adjust the rate of delivery of the content item based on the rate at which users interact with the content item.

Abstract: An online system receives content items from content providers and delivers the content items to client devices of users. The online system receives a weight associated with an item described in the content item. The online system determines a rate at which a content item is delivered to users based on the received weight associated with the item and a rate at which users interact with the content item. The online system delivers the content item to users at the rate determined based on the received weight and the rate at which users interact with the content item. The online system may periodically adjust the rate of delivery of the content item based on the rate at which users interact with the content item.

Abstract: An online system trains a machine learning model for providing content items to users of the online system. The online system logs actions performed by users and generates user feature vectors based on the logged actions. The online system generates item feature vectors based on information about items from third parties. The machine learning model is trained using the user feature vectors and item feature vectors. The machine learning model determines a likelihood that a target user will acquire a certain item, especially after an update or change has occurred relating to that item. The online system selects content items that the target user is likely to be interested in and is likely to interact with.

Abstract: An online system generates a taxonomy to classify objects that resemble each other. To compare different objects against each other, the online system generates canonical form data structures to represent the objects. The online system uses the canonical form data structures to standardize unstructured information about objects, for example, objects received from different sources of information to generate the taxonomy. The online system can determine a level of resemblance between objects based on parameter values of the canonical form data structures. The online system uses the taxonomy to exclude content items that are unlikely to be of interest to a user of the online system. The taxonomy may be represented by a graph data structure including nodes connected by edges.

Abstract: An online system trains a machine learning model for providing content items to users of the online system. The online system logs actions performed by users and generates user feature vectors based on the logged actions. The online system generates item feature vectors based on information about items from third parties. The machine learning model is trained using the user feature vectors and item feature vectors. The machine learning model determines a likelihood that a target user will acquire a certain item, especially after an update or change has occurred relating to that item. The online system selects content items that the target user is likely to be interested in and is likely to interact with.

Abstract: A content publishing system receives content items from content provider systems for providing to users. The content publishing system further receives mapping tables from the content provider systems specifying weights for users of the content provider systems. The content publishing system provides content items to users based on the user specific weights received from the content provider systems. As a result, a content provider system can identify users that are likely to be interested in specific content items and assigns weights to these users to adjust the likelihood of the users receiving appropriate content items via the content publishing system.

Abstract: An online system receives content items from content providers and delivers the content items to client devices of users. The online system receives a weight associated with an item described in the content item. The online system determines a rate at which a content item is delivered to users based on the received weight associated with the item and a rate at which users interact with the content item. The online system delivers the content item to users at the rate determined based on the received weight and the rate at which users interact with the content item. The online system may periodically adjust the rate of delivery of the content item based on the rate at which users interact with the content item.

Abstract: A content item maintained by an online system has a creative presenting content including a product from an application associated with a third party system. When the online system identifies an opportunity to present the content item to the user, the online system selects a product associated with the third party system based on content from one or more third party systems accessed by the user. The online system includes the content item with the creative including content from the application including the selected product in one or more selection processes. If the content item with the creative including content from the application including the selected product is presented to the user and the online system receives an indication the application was installed on a client device, the online system provides instructions to the client device to present content associated with the selected product.

Abstract: An online system generates a taxonomy to classify objects that resemble each other. To compare different objects against each other, the online system generates canonical form data structures to represent the objects. The online system uses the canonical form data structures to standardize unstructured information about objects, for example, objects received from different sources of information to generate the taxonomy. The online system can determine a level of resemblance between objects based on parameter values of the canonical form data structures. The online system uses the taxonomy to exclude content items that are unlikely to be of interest to a user of the online system. The taxonomy may be represented by a graph data structure including nodes connected by edges.

Abstract: An online system trains a machine learning model for providing content items to users of the online system. The online system logs actions performed by users and generates user feature vectors based on the logged actions. The online system generates item feature vectors based on information about items from third parties. The machine learning model is trained using the user feature vectors and item feature vectors. The machine learning model determines a likelihood that a target user will acquire a certain item, especially after an update or change has occurred relating to that item. The online system selects content items that the target user is likely to be interested in and is likely to interact with.

Abstract: A content publishing system receives content items from content provider systems for providing to users. The content publishing system further receives mapping tables from the content provider systems specifying weights for users of the content provider systems. The content publishing system provides content items to users based on the user specific weights received from the content provider systems. As a result, a content provider system can identify users that are likely to be interested in specific content items and assigns weights to these users to adjust the likelihood of the users receiving appropriate content items via the content publishing system.

Abstract: An online system receives an advertisement request from an advertiser and determines an advertisement objective associated with the advertisement request. Validation rules associated with the advertisement request are retrieved and applied to components of the advertisement request. Application of the validation rules determines whether components of the advertisement request are consistent with the advertisement objective. A result of the application of the validation rules to the advertisement request is presented to the advertiser, providing the advertiser with a measure of the effectiveness of the advertisement request in satisfying the advertisement objective.