Facebook, Inc.

Microsoft Technology Licensing, LLC

Meta Platforms, Inc.

Avi Samuel Gavlovski

Zhurun Zhang

Aditya Pradip Kulkarni

Junbiao Tang

Benjamin Edward Rampson

Robert Alan Meyers

Anand Sumatilal Bhalgat

Hao Zhang

Henning Korsholm Rohde

Poornima Hanumara

Sachin Patney

Hao Song

Bala Neerumalla

Jeremy Jude Alexi Edwards

Zhonghua Qu

Yevgeniya Solyanik

James Theodore Kleban

David Benjamin Lue

Anwar Saipulla

George Xiangwen Zeng

An online system receives multiple candidate components for including in content items to be presented to online system users. Upon identifying an opportunity to present content to a subject user of the online system, the online system dynamically generates an optimal content item for presentation to the subject user that includes one or more candidate components. Candidate components included in the optimal content item are associated with a predicted marginal effect on a performance metric associated the optimal content item. This marginal effect may be predicted using a machine-learned model that is trained using historical performance information about content items that were presented to viewing users of the online system having at least a threshold measure of similarity to the subject user and one or more features associated with candidate components included in these content items and in the optimal content item.

Selecting one or more components to be included in a content item optimized for an online system user

An online system generates dynamically optimized content items composed of creatives selected from a set of creatives provided by a content provider according to a set of rules associated with the creatives. Creatives include the title, image, video, descriptive text and other different types of components. The online system also receives rules describing one or more actions that can be performed on each of the creatives and under what condition for the assembly of the content item. For a target user of the content item, the online system applies the rules to remove creatives that violate the rules. Each creative that satisfies the rules is analyzed and ranked based on the likelihood that the target user will interact with a content item that includes that particular creative. For a different user, a different sponsored content item having different creatives chosen from the same set of creatives is generated.

Dynamic creative optimization rule engine for effective content delivery

An online system receives multiple candidate components for including in content items to be presented to online system users. Upon identifying an opportunity to present content to a subject user of the online system, the online system dynamically generates an optimal content item for presentation to the subject user that includes one or more candidate components. Candidate components included in the optimal content item are selected by predicting an affinity of the subject user for each candidate component. The affinity of the subject user for a candidate component may be predicted using a machine-learned model that is trained using historical performance information about content items including the candidate component that were presented to viewing users of the online system having at least a threshold measure of similarity to the subject user. Components of content items used to train the model may be selected using a heuristic (e.g., Thompson sampling).

Generating data to predict user affinity for a component to be included in a content item optimized for an online system user

An online system generates dynamically optimized sponsored content for a target user of the online system. Each sponsored content item comprises optimal creatives selected for a target user from a set of creatives provided by a content provider. Each type of creative (e.g. title, image, video, descriptive text), has a trained creative model to generate a prediction score for a creative of the same type based on the features of the creative and the characteristics of the target user. The prediction score of a creative indicates the likelihood that the target user will interact with a sponsored content item that includes that particular creative. The online system selects a creative for each type and assembles the selected creatives into a sponsored content item for the target user. For a different user, a different sponsored content item having different creatives chosen from the same set of creatives is generated.

Dynamic creative optimization for effectively delivering content

An online system receives a set of creatives provided by a content provider, and presents one or more pseudo-assembled content items composed of the different combinations of the received creatives on a user interface to the content provider. A pseudo-assembled content item includes one or more creatives to be included in a final content item that are placed in their positions in the display interface, but the content item has not yet undergone assembly or creation. The positions of the creatives are defined by one or more placement rules provided by the content provider. The content provider can interact with the user interface to swap different creatives into the content item. The content provider can visually preview different content item candidates assembled from different permutations of creatives from the set of creatives of the content item before creating the final content item.

Preview of content items for dynamic creative optimization

Concepts and technologies are described herein for providing a range filter user interface with selectable range controls that toggle between inclusive and exclusive modes. The range controls visually indicate configuration in an inclusive mode or an exclusive mode. Upon selection of a range control, the range control switches between inclusive and exclusive modes, and provides visual indication of the current mode.

Inclusion/exclusion user interface controls for range filters

Program source code is annotated to support dataflow analysis or other program analysis, without requiring changes to compilers. Annotation statements are embedded inside comments or other non-code-generative portions of the source code. The annotations can be used to express contracts at routine boundaries, allowing an analyzer to check the global correctness of the source code through modular (local) analysis, with performance that is linear in the number of routines. In particular, annotated SQL source code may be analyzed to identify SQL injection vulnerabilities.

Embedded annotation and program analysis

Growing community of inventors

Kirkland, WA, United States of America

Avi Samuel Gavlovski