Microsoft Technology Licensing, LLC

Linkedin Corporation

Anmol Bhasin

Abhishek Gupta

Christian Posse

Yurong Shi

Jian H Li

Sachin Rekhi

Baoshi Yan

Angela Yoonjeong Yang

Annabel Fang Liu

Jacob Kessler

Monica Rogati

Junghoon (Andrew) Ahn

Ramesh Dommeti

Jiong Wang

Alexis Pribula

Mohammad Shafkat Amin

Zang Li

Wing Li

Kun Liu

Joel Daniel Young

Lijun Tang

Xu Miao

Yitong Zhou

Dmytro Andriyovich Ivchenko

Elizabeth Ethel Burstein

Venu Javarappa

Junghoon Andrew Ahn

Parker R Barrile

Xiao Li

Bo Long

Deepak Kumar

Sanjay Sureshchandra Dubey

Ye Xu

Craig Martell

Yevgeniy Brikman

Vita G Markman

Praveen Neppalli Naga

Yanen Li

Lizabeth Li

Lili Wu

Shernaz R Pavri

Haishan Liu

Jonathan David Traupman

Jieying Chen

Paul Taylor Ogilvie

Adam Nash

Liang Tang

Vikram Rangnekar

Trevor Walker

Zal Yaz Bilimoria

Sripad Sriram

Ahmet Bugdayci

Jiansheng Huang

Bhaskaran Devaraj

Tarun Kumar

Deepak Argawal

Xiangrui Meng

Rudolph Jakob Heuser

Michael D Repass

Jonathan Wyatt Seitel

Hemendra Kumar

Systems and methods for displaying a user interface object associated with a job candidate's social networking site proximate to a job listing presented by a website are described. When a job candidate selects the user interface object, the systems and methods identify and/or obtain information associated with the job candidate that is located or otherwise stored at the social networking site of which the job candidate is a member. Once the information is identified and/or obtained, the systems and methods provide the information to the website, such as to a job application submission system associated with the website.

Applying for a job using a mobile computing device

Techniques for identifying and presenting member profiles similar to a source member profile are described. With some embodiments, a general recommendation engine is used to extract features from member profiles, and then store the extracted features, including any computed, derived or retrieved profile features, in an enhanced member profile. In real-time, the general recommendation engine processes client requests to identify member profiles similar to a source member profile by comparing select profile features stored in the enhanced member profile with corresponding profile features of the source member profile, where the comparison results in several similarity sub-scores that are then combined in accordance with directives set forth in a configuration file. Finally, the member profiles with the highest similarity scores corresponding with the user-selected member profile are selected, and in some instances, presented to a user.

Suggesting candidate profiles similar to a reference profile

The disclosed embodiments provide a method and system for performing regularized model adaptation for in-session recommendations. During operation, the system obtains, from a server, a first global version of a statistical model. During a first user session with a user, the system improves a performance of the statistical model by using the first global version to output one or more recommendations to the user and using the first global version and user feedback from the user to create a first personalized version of the statistical model. At an end of the first user session, the system transmits an update containing a difference between the first personalized version and the first global version to the server for use in producing a second global version of the statistical model by the server.

Regularized model adaptation for in-session recommendations

Techniques for leveraging a social graph to facilitate the delivery of relevant recommendations. For example, a recommender is identified based on the recommender being a member of a social networking service who has interacted with an item of web-based content. A recommendee is identified based on the recommendee being another member of the social networking service who is connected to the recommender via a social graph maintained by the social networking service and based on having an affinity score for the item that exceeds a recommendee affinity score threshold and a connection strength to the recommender that exceeds a connection strength threshold. The recommender is sent a communication that invites the recommender to recommend the item to the recommendee. With some example embodiments, the communication is sent to the recommender within a pre-determined time measured from the time the recommender initiated an interaction with the item of web-based content.

Leveraging a social graph to deliver relevant recommendations

A system and method for managing asynchronously receiving updates and merging updates into global versions of a statistical model using version control are disclosed. During operation, the system transmits a first global version of a statistical model to a set of client computer systems. Next, the system obtains, from a first subset of the client computer systems, a first set of updates to the first global version. The system then merges the first set of updates into a second global version of the statistical model. Finally, the system transmits the second global version to the client computer systems asynchronously from receiving a second set of updates to the first and/or second global versions from a second subset of the client computer systems.

Version control for asynchronous distributed machine learning

Disclosed in some examples are methods, systems and machine readable medium for recommending an out-of-network communication by determining a set of potential recommended members of a social networking service based upon one or more recommendation criteria. In some examples the recommendation criteria may include: a profile similarity to a previous target of an out-of-network communication, a degree of correspondence between an interest and intent of the sending member, and a likelihood of response.

Suggested out of network communication recipients

A method and system for providing account recommendations is disclosed. A server system stores sales data for a first member, wherein sales data includes profile information for one or more individual customers. The server system analyzes the profile information for one or more of the individual customers to identify one attributes associated with the customers. The server system determines one or more additional members with member profiles that include the one or more identified attributes. For a respective additional member in the at least one of the determined additional members the server system determines, based on stored information about the respective additional member, an respective organization associated with the at least one determined additional member; and selects the respective organization as an account recommendation.

Account recommendations

Techniques for generating recommendation cluster within a social network service are described. Consistent with some embodiments, sample members in a social network service are identified. The sample members may be associated with prior member activity involving a source member. A cluster category this then selected based on a member attribute shared by a plurality of the sample members. In turn, a recommendation cluster is generated based on the selected cluster category. Generating the recommendation duster may involve selecting member profiles that match the cluster category. The member profiles selected in this way form the recommendation cluster. One or more of the member profiles of the recommendation cluster are then surfaced to a client device operated by the source member.

Generating recommendation clusters in a social network

A method and system for providing lead recommendations are disclosed. A server system stores profile information for a plurality of members of a server system. The server system then analyzes the stored profile information to identify one or more potential sales lead recommendations for a first member of the server system. The server system then ranks the one or more identified potential sales lead recommendations. The server system selects one or more of the identified sales lead recommendations and transmits the selected one or more identified sales lead recommendations to a client device associated with the first member of the server system.

Lead recommendations

A first user of a presentation machine may be a recruiter that initiates an action in reference to a first user profile. The first user profile may describe a first candidate for a job. The presentation machine may identify the first user profile and determine a similarity score that indicates a degree of similarity between the first user profile and a second user profile that describes a second candidate for the job. The presentation machine may also access a volatility score that indicates a likelihood that the second candidate is receptive to a proposal that the second candidate be employed by an employer. Based on the similarity score and on the volatility score, the presentation machine may determine a rank of the second user profile. Based on the determined rank, the presentation machine may present the second user profile to the first user.

Presenting a user profile

A method and system for providing account recommendations is disclosed. A server system stores sales data for a first member, wherein sales data includes profile information for one or more individual customers. The sewer system analyzes the profile information for one or more of the individual customers to identify one attributes associated with the customers. The server system determines one or more additional members with member profiles that include the one or more identified attributes. For a respective additional member in the at least one of the determined additional members the server system determines, based on stored information about the respective additional member, an respective organization associated with the at least one determined additional member; and selects the respective organization as an account recommendation.

A system and method for temporal-based professional similarity are provided. In example embodiments, a request to identify, from among a plurality of member profiles of a social network service, a profile that is similar to a source profile, is received. Profile data of the source profile and a candidate profile are accessed from the social network service. Profile features are extracted from the profile data. The profile features include source features extracted from the profile data of the source profile and candidate features extracted from the profile data of the candidate profile. Respective profile features correspond to temporal data included in the profile data. Data structures are generated by structuring the profile features according to the temporal data. The data structures include a source data structure generated using the source features and a candidate data structure generated using the candidate features. A profile similarity score is determined by comparing the candidate data structure with the source data structure. The profile similarity score indicates the similarity between the candidate profile and the source profile.

Temporal-based professional similarity

This disclosure provides systems and methods for determining a classification model for a secondary language different from a primary language. A social networking server is configured to obtain primary language content written in a first spoken language and secondary language content written in a second spoken language. The social networking server further obtains a machine translation of the primary language content. The social networking server then determines an initial language model from the machine translation. The social networking further determines a language model perturbation using the initial language model, where the language model perturbation accounts for a difference between the machine translation and the secondary language content. The social networking server also determines a classification model from the initial language model and the language model perturbation, which is then applied to a plurality of comments associated with an item of interest provided by a social networking service.

Transfer learning for bilingual content classification

Systems and methods are disclosed for determining whether a short amount of text is irrelevant. Initially, an article is selected having one or more comments of varying length. Depending on the number of comments available, a native context may be constructed based on a given comment and other neighboring comments. In other embodiments, a transferred context may be constructed from the given comment and topically similar comments extracted from other, topically similar articles. A native context-aware feature may be determined from the constructed native context and a transferred context-aware feature may be determined from the constructed transferred context. These features may be leveraged by a language classifier to determine whether a given comment is irrelevant.

Context-aware approach to detection of short irrelevant texts

Growing community of inventors

Los Altos, CA, United States of America

Anmol Bhasin