Abstract: An online system receives a request from a user of a manager transmitter to generate a unique beacon identifier (ID) associated with a physical location. Responsive to receiving the beacon ID from the online system, the manager transmitter transmits a Bluetooth signal comprising the beacon ID to user client devices, which send the beacon ID to the online system for identification. Responsive to detecting that a received signal strength exceeds a threshold, a location context module classifies the instance of the user client device detecting the signal as an example of a user being present at the physical location. A location prediction module uses the instance as training data to train a machine-learning model to predict the presence of online system users at the physical location.

Abstract: An online system receives a request from a user of a manager transmitter to generate a unique beacon identifier (ID) associated with a physical location. Responsive to receiving the beacon ID from the online system, the manager transmitter transmits a Bluetooth signal comprising the beacon ID to user client devices, which send the beacon ID to the online system for identification. Responsive to detecting that a received signal strength exceeds a threshold, a location context module classifies the instance of the user client device detecting the signal as an example of a user being present at the physical location. A location prediction module uses the instance as training data to train a machine-learning model to predict the presence of online system users at the physical location.

Abstract: An online system provides a content data model to content providers for optimizing content creation. The content data model is a hierarchical model with multiple levels for content creation, e.g., campaign level, content item set level and content item level. At each level of the content data model, a content provider can specify certain information concerning the content creation at that level, such as optimization goal for each level. The information specified at each level of the content data model is applied to all elements under that level by the online system during the content creation process. With the content data model, a content provider can efficiently design creative campaigns by specifying objectives, optimization goals, target audiences and budgets, etc., at different design levels. The online system dynamically optimizes content item creation based on information about creatives to be included in a content item for a target user.

Abstract: An online system receives information from client devices describing locations of online system users and identifies certain events based on the information. To account for different rates at which information is received from client devices when identifying events, the online system identifies a group of users associated with location information received at greater than a threshold rate and an alternative group of users associated with information received at less than the threshold rate. Based on a value associated with the group and an additional value associated with the alternative group, the online system computes a scaling factor that is applied to the additional value, allowing the online system to account for potential events associated with the alternative group that were not identified because of the lower rate at which the online system received location information associated with users in the additional group.

Abstract: A target audience for an ad campaign is determined during an exploration period of the ad campaign by modifying the target audience based on the fulfillment of performance objectives. An initial target audience may be provided by the advertiser or determined by the social networking system based on ad campaigns having similar ad content or other similar characteristics. Advertisements associated with the ad campaign are served to users of the initial target audience. A subset of the target audience that fulfills the performance objectives of the ad campaign is identified and those users are used to generate a new targeting audience to target users that “look like” the subset of the target audience. The new targeting audience is used in place of the initial target audience to improve targeting for the advertisement. This process may be iteratively performed to refine the target audience during the exploration period.