Facebook, Inc.

Aude Hofleitner

Pierre Moreels

Vincent Gonguet

Bogdan State

Sofus Attila Macskassy

Tsuwei Chen

Aruna Bharathi

Andreas Gros

Zoe Abrams Bayen

Scott J Bratsman

Jacob Perkowski

Steven James Jarrett

Zhiliang Ma

In one embodiment, a method includes accessing a location history of a user of a social-networking system. The social-networking system includes a social graph that includes multiple nodes and edges connecting the nodes. At least node corresponds to the user. The method includes accessing a data set from a third-party source independent of the social-networking system. The data set references one or more locations. The method includes comparing the location history of the user with the locations referenced by the data set to determine an overlap between the location history and the data set and determining based on the comparison one or more labels to assign to the user or to one or more locations where the location history and the data set overlap.

Analyzing geo-spatial data in layers

Systems, methods, and non-transitory computer-readable media can collect past user information and churn data for a plurality of users. A churn prediction model is trained using the past user information and churn data. A churn propensity score is calculated for a present user based on the churn prediction model, the churn propensity score indicative of the likelihood of the present user to churn.

Systems and methods for churn prediction

Systems, methods, and non-transitory computer-readable media can acquire shape data representative of one or more polygons. At least one serialization format can be produced based on the shape data. The at least one serialization format can be packaged into a proprietary package that is representative of the one or more polygons. At least a portion of the proprietary package can be utilized for one or more applications.

Systems and methods for processing shape data based on serialization formatting

In one embodiment, a method includes, for each of multiple interactions by a user with an online service, collecting: device information describing a device used by the user for the interaction; access information describing how the user accessed the online service for the interaction; and a count value of the interaction. The method further includes determining based on the collected information a historical count value for each of one or more particular combinations of device and access information.

Daily counts and usage probabilities for a user of an online service

Techniques for wireless transmitter location detection are described. An apparatus may comprise a processor circuit and a location database generator component. The location database generator component may comprise: a logging component operative on the processor circuit to receive a plurality of location data packages, the location data packages comprising locations and associated wireless transmitter identifiers, and to log the location data packages into a location database, the location database comprising a plurality of tuples of the locations and the wireless transmitter identifiers; and an analysis component operative on the processor circuit to construct a transmitter mapping from wireless transmitter identifiers to locations based on the plurality of tuples of the location database. Other embodiments are described and claimed.

Techniques for wireless transmitter location detection

Exemplary methods, apparatuses, and systems store an identifier for a user device when the user device is determined to be accessing a network service and store a time at which the user device is determined to be accessing the network service for each instance of the user device being determined to be accessing the network service. Periods of time during each day of the week in which the user device is likely to accessing to the network service are determined based upon the stored identifier and times. Whether the user is likely to access the network service while at work or at home is determined based upon the determined periods of time in which user devices are likely to be accessing the network service.

Growing community of inventors

San Francisco, CA, United States of America

Aude Hofleitner