Abstract: 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.

Abstract: A technique is described herein for reliably comparing a first route produced by a first routing system with a second route produced by a second routing system. In some implementations, the technique includes: generating an envelope that encloses second-route data associated with the second route; identifying a segment of the first route having first-route data points that lie outside the envelope; classifying a cause of a deviation associated with the segment based on segment data that describes the segment; and performing an action based on classification of the deviation. The technique is fast, resource efficient, accurate, and resilient to the fact that the first and second routing systems potentially use different rules and/or map data to produce their routes. The results of the technique can be leveraged to improve the performance of the first routing system.

Abstract: Various embodiments discussed herein relate to route optimization and query understanding for route and/or direction queries with complex user preferences. Each route candidate, for example, is treated as a richly annotated document. The routing engine, in addition to performing route optimization, acts as a retriever and ranker of route documents according to user intent. Various embodiments rank routes not just based on a simple cost model, but based on many more or alternative factors according to user preferences, user intent, and/or contextual data.

Abstract: 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.

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: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

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: 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.

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: 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.

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: 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.

Abstract: 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.

Abstract: 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.