Microsoft Technology Licensing, LLC

Linkedin Corporation

Alexis Blevins Baird

Xin Fu

Jason Schissel

Yu Long Cao

Yang Zhou

Daniel Tunkelang

Nikita Igorevych Lytkin

Baoshi Yan

Erik Eugene Buchanan

Benjamin John McCann

Lokesh Pooranmal Bajaj

John Robert Jersin

Yin Lou

Ganesh Ramesh

Sathyanarayan Anand

Raviraj Jain

Jiaqi Guo

Lixin Feng

Techniques for dynamically altering weights to re-weight attributes of an ordering model based on feedback in a streaming environment are described. In an embodiment, a system accesses, based on a candidate stream definition comprising a role including a title, one or more stream-related information sources, and extracts attributes from the sources. Additionally, the system inputs the attributes to a combined ordering model that is trained by a machine learning algorithm to output ordering scores for member profiles of an online system (e.g., hosting a social networking service). The combined ordering model includes weights assigned to the attributes. Moreover, the system orders, based on the ordering scores, the profiles. Furthermore, the system presents, on a display, of top-ordered profiles. Then, the system accesses feedback regarding the top-ordered profiles and dynamically trains the weights assigned to each of the attributes to alter the weights assigned to the attributes based on the feedback.

Using feedback to create and modify candidate streams

Techniques for dynamically generating feedback based on contextual information and providing the feedback to a user are provided. A service provider determines, based on contextual information related to a user (such as personal information previously provided by the user) interactive data to display to the user. The type of interactive data may correspond to the type of personal information submitted by the user or derived by the service provider. The interactive data may be based on other users that have already registered with the service provider. In this way, a user is able to (1) view current and relevant information that is related to the user and (2) see the value that the user receives by providing additional personal information. Subsequent interactive data may be based on multiple personal data items that the service provider receives from the user. These techniques are also applicable after a user has registered with a service provider.

Dynamically generating feedback based on contextual information

Techniques for tracking profile completeness among members of an online social networking system are described. According to various embodiments, profile completion score criteria information identifies a profile completion score weight value associated with each of a plurality of member profile fields available in member profiles of an online social networking service. A specific member profile associated with a specific member of the online social networking service is accessed, and one or more of the plurality of member profile fields that have been completed in the specific member profile are identified. Thereafter, the profile completion score weight values associated with the member profile fields that have been completed in the specific member profile are determined, based on the profile completion score criteria information. Based on the determined profile completion score weight values, a profile completion score is then generated for the specific member profile.

Profile completion score

Techniques for optimizing a guided edit process for editing a member profile page are described. According to various embodiments, incomplete member profile fields in a member profile associated with member of an online social networking service are identified. Profile completion score weight values associated with the incomplete member profile fields in the member profile are then determined. Thereafter, the incomplete member profile fields in the member profile are ranked, based on the profile completion score weight values associated with each of the incomplete member profile fields. A list of one or more of the highest ranked incomplete member profile fields are then displayed, together with a prompt recommending the member to complete the identified incomplete member profile fields.

Guided edit optimization

Disclosed in some examples is a method including receiving a plurality of transaction records, each of the transaction records including data about a particular transaction engaged in by a member of a social networking service and including a geographic location and a timestamp of the particular transaction; scoring each of the plurality of transaction records based upon the recency of the transaction; clustering the plurality of transaction records into a plurality of clusters, each cluster including transaction records which contain similar geographic locations; creating an aggregate score for each particular one of the plurality of clusters based upon a sum total of the scores calculated for each transaction record clustered into the particular cluster; and creating a probability distribution based upon the scores for the plurality of clusters, the probability distribution indicating a probability that the member was in each of the plurality of locations represented by the clusters.

Techniques for inferring a location

A system, apparatus, computer-program product and method are provided for identifying members of a particular user segment. One particular user segment of interest includes members who work for employers having a number of employees within a predetermined range. Members of an online service provide data purporting to identify their employers and/or other personal or professional attributes. The data entries are normalized by standardizing terms, removing superfluous or unneeded terms, and/or performing other processing. The members are then clustered according to their normalized employer names, and members within clusters that have sizes within the range are added to the user segment. Invalid employer names (e.g., fictitious companies, non-existent entities) may be filtered out. Within a cluster, a professional social networking site (or other site) may be analyzed to determine if the clustered members have developed relationships; if not, the cluster may be cancelled.

System and method for determining users working for the same employers in a social network

Growing community of inventors

San Francisco, CA, United States of America

Alexis Blevins Baird