Facebook, Inc.

Microsoft Technology Licensing, LLC

Meta Platforms, Inc.

Goran Predovic

Chaochao Cai

Liang Xu

Bodin Dresevic

Li Zhou

Aleksey Sergeyevich Fadeev

Yimin Song

Milan Vukosavljevic

Logan Michael Gore

Qing Li

Nikola Letic

Paul A Viola

Wei Wei

Stephane Taine

Ahmad A Abdulkader

Fei Su

Jennifer A Teed

Dragomir Dimitrov Yankov

Mudit Agrawal

Eric Christian Brown

Jen Anderson

Bogdan Radakovic

Vashutosh Agrawal

Sergiy Dubynskiy

Michael Robert Evans

Nikola Todic

Aleksandar Samardzija

Antonios Karatzoglou

Mohit Khanna

Ying Jiang

Tijana Bekic

Varun Kakkar

Nikola Perin

Jacob Nicholas Whitbeck

Chang Liu

Bruce Edward James

Jie Zhang

Maybelle Lippert

Pu Zhang

Dejan Ivkovic

A technique automatically identifies and resolves prohibited maneuvers in candidate routes generated by a routing system. Examples of prohibited maneuvers include traveling over a non-navigable path, traveling in an incorrect direction over a roadway, and an improper turn. The technique determines whether the candidate routes contain prohibited maneuvers by comparing the candidate routes with plural types of route-related validation data in plural respective validation processes. For example, a first validation process compares the candidate routes with a collection of GPS traces. A second validation process compares the candidate routes with map reference data. The technique further includes provisions for correcting the causes of identified prohibited maneuvers. Overall, the technique reduces the amount of manual effort involved in verifying the accuracy of routes produced by the routing system, and improves the accuracy, reliability, and safety of the routing system.

Identifying and resolving prohibited maneuvers in routes generated by a routing system

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&#x2122; 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.

Image based user identification across multiple online systems

A method for predicting demographic information for a common user that is associated with a plurality of unresolved identifiers. An unresolved identifier defines a context in which a client device accesses one or more online systems, the context not determined to be associated with a specific user. The method comprises identifying a set of unresolved identifiers, and identifying information describing one or more access events associated with each unresolved identifier. For each pair of unresolved identifiers, a similarity score for the pair is determined based on the identified information. Responsive to the similarity score exceeding a threshold similarity score, the pair of unresolved identifiers is clustered, the clustering indicating a prediction that the pair of unresolved identifiers are associated with a common user. Predicted demographic information is determined for each unresolved identifier in the cluster. Based on predicted demographic information determined for each unresolved identifier in the cluster, aggregate demographic information is determined for the common user.

Predicting demographic information using an unresolved graph

Information describing deliveries of content items and user actions associated with the content items is stored. Each delivery is performed by an online publisher to a user. A user action associated with a content item performed by a target user is detected. Information describing a set of online publishers that delivered the content item to the target user is retrieved. For each online publisher of the set, a likelihood that the user action would have occurred without the online publisher's delivery of the content item to the target user is determined. An estimated increase in the likelihood that the user action occurred due to the online publisher's delivery of the content item to the target user is determined. A performance metric is determined for the online publisher, wherein ratios of performance metrics for the set of online publishers are related based on corresponding ratios of the estimated increases in likelihoods.

Determining performance metrics for delivery of electronic media content items by online publishers

A user action associated with a content item performed by a target user is detected. Information describing online publishers that delivered the content item to the target user is retrieved. For each publisher, a likelihood that the user action would have occurred without the publisher's delivery of the content item to the target user is determined. An estimated increase in the likelihood that the user action occurred due to the publisher's delivery of the content item to the target user is determined. A baseline value indicating a likelihood that the user action would have occurred without delivery of the content item to the target user by any publishers is estimated based on attributes for the target user. A performance metric is determined for each publisher, wherein ratios of the metrics are scaled based on the baseline value and are related based on corresponding ratios of the estimated increases in likelihoods.

Determining performance metrics for delivery of electronic media content items by online publishers scaled using a baseline conversion rate

An online system promotes physical store visits by presenting users with content items for a physical store location and subsequently logs visits of online system users to the physical store location to track performance of a campaign associated with the presented content item. The online system registers attention events associated with the presented content items presented to users on third party publishing sites via tracking pixels and registers attention events as store front visit conversion events if, within a predetermined period of time from a valid attention event, a user has subsequently gone in and visited the physical store front location.

Physical store visit attribution

A method for providing content items to one or more client devices associated with at least one unresolved identifier. An unresolved identifier defines a context in which a client device accesses one or more online systems, the context not determined to be associated with a specific user. The method comprises identifying a set of unresolved identifiers, and identifying information describing one or more access events associated with each unresolved identifier. For each pair of unresolved identifiers, a similarity score for the pair is determined based on the identified information. Responsive to the similarity score exceeding a threshold similarity score, the pair of unresolved identifiers is clustered, the clustering indicating a prediction that the pair of unresolved identifiers are associated with a common user. Based on this clustering, a content item is displayed on or more user devices associated with at least one unresolved identifier of the set of unresolved identifiers.

User targeting using an unresolved graph

Disclosed is an online system that infers interests of unresolved users for whom the interests are not known. The online system determines certain features about the unresolved users, but does not have certain information about the users themselves (e.g., their interests), so instead infers these attributes based on the features of the user. The online system provides the features as input to a classifier trained to predict a particular interest, and the classifier outputs a prediction of whether the user has the corresponding interest. In one embodiment, the online system trains a classifier for various interest values by forming training sets for the interests using the features for users who are logged into the online system and hence have known interests.

Interest prediction for unresolved users in an online system

A method for determining reach of a content item that is displayed on one or more client devices associated with at least one unresolved identifier. An unresolved identifier defines a context in which a client device accesses one or more online systems, the context not determined to be associated with a specific user. The method comprises identifying a set of unresolved identifiers, and identifying information describing one or more access events associated with each unresolved identifier. For each pair of unresolved identifiers, a similarity score for the pair is determined based on the identified information. Responsive to the similarity score exceeding a threshold similarity score, the pair of unresolved identifiers is clustered, the clustering indicating a prediction that the pair of unresolved identifiers are associated with a common user. Finally, for the reach of the displayed content item is determined based on the clustering of the set of unresolved identifiers.

Predicting reach of content using an unresolved graph

An online system determines one or more metrics describing consumption of content by various users by identifying users of the online system capable of being identified based on information received from multiple client devices. For example, the online system identifies users associated with user identifiers that are also associated with other types of identifying information (e.g., cookies, device identifiers). From the identified users, the online system generates a set of users based on a distribution of characteristics. The distribution of characteristics may be determined by the online system as characteristics of a group of users or received by the online system from a third party system and describes characteristics of users of the third party system. Based on interactions with content by users in the set, the online system determines one or more metrics describing consumption of content.

Accounting for bias of user characteristics when determining consumption of content by online system users

An online system predicts gender, age, interests, or other demographic information of a user based on image data of the user, e.g., profile photos, photos the user posts of him/herself within an online system, and photos of the user posted by other users socially connected with the user, and textual data in the user's profile that suggests age or gender (e.g., like or dislikes similar to a population of users of an online system). The online system similarly predicts a user's interests based on the photos of the user. The online system applies one or more models trained using deep learning techniques to generate the predictions. The online system uses the predictions to build more information about the user in the online system, and provide improved and targeted content delivery to the user that may have disparate information scattered throughout different online systems.

Image based prediction of user demographics

User inputs can indicate an intent of a user to target a location on a display. In order to determine a targeted point based on a user input, a computing device can receive an indication of at least one point, an indication of a width, and an indication of a height. The computing device can estimate a portion of the display based on the indication of the at least one point, the indication of the width, and the indication of the height. The computing device can also determine the targeted point based on a location of the at least one point and based on a location of a portion of one or more objects within the estimated portion of the display.

Touch intelligent targeting

Growing community of inventors

Redmond, WA, United States of America

Goran Predovic