Microsoft Technology Licensing, LLC

Benjamin Hoan Le

Shakti Dhirendraji Sinha

Dhruv Arya

Ganesh Venkataraman

Aman Grover

Qing Duan

Liang Zhang

Kun Liu

Parul Jain

Anthony Duane Duerr

Vijay K Dialani

Saurabh Kataria

Wen Pu

Xiaowen Zhang

Nadia Fawaz

Caleb Timothy Johnson

Kevin Kao

Zhifeng Deng

Guoyin Wang

The disclosed embodiments provide a system for processing data. During operation, the system performs processing related to a first set of features for a first entity using a first series of embedding layers, wherein the processing includes applying each embedding layer in the first series of embedding layers to a concatenation of all outputs of one or more layers preceding the embedding layer. Next, the system obtains a first embedding as an output of a first final layer in the first series of embedding layers. The system then outputs the first embedding for use by a machine learning model.

Entity pyramid embeddings

The disclosed embodiments provide a system for processing data. During operation, the system obtains events reflecting responses by a user to job recommendations outputted to the user. Next, the system updates a set of features for the user from the events. The system then includes the updated set of features in a feature repository for use by a statistical model in generating a ranking of jobs for the user. Finally, the system retrains the statistical model using the events prior to using the statistical model to update the outputted job recommendations using the ranking.

Nearline updates to personalized models and features

In an example, features in a boosting decision tree model are initialized to zero, the boosting decision tree model located in a GLMM and connected to a deep neural network collaborative filtering model via a prediction layer. While the features in the boosting decision tree model remain zero, the deep neural network collaborative filtering model is trained. One or more trees in the boosting decision tree model are boosted using logits produced by the training of the deep neural network collaborative filtering model as a margin. The prediction layer is trained using features from the deep neural network collaborative filtering model and features from the boosting decision tree model. It is then determined whether a set of convergence criteria is met. If not, then the deep neural network collaborative filtering model is retrained using the features and the process is repeated until the set of convergence criteria is met.

Deep and wide machine learned model for job recommendation

In an example embodiment, one or more query terms are obtained. For each of the one or more query terms, a standardized entity taxonomy is searched to locate a standardized entity that most closely matches the query term. A confidence score is calculated for the query term-standardized entity pair for the standardized entity that most closely matches the query term. In response to a determination that the confidence score transgresses a threshold, the query term is associated with an entity identification corresponding to the standardized entity that most closely matches the query term. One or more query rewriting rules corresponding to an entity type of the standardized entity having the entity identification are obtained. The one or more query rewriting rules are executed to rewrite the first query such that the rewritten query, when performed on a data source, returns fewer search results than the first query would have.

Entity based query filtering

Instead of a fixed fee for a particular job application, discussed in some examples are methods, systems, and machine readable mediums which provide for a job posting service that utilizes a pay-per-click model. That is, job posters pay a fee for each time the member selects the job posting for further inquiry when that posting is shown to a member (called an impression). The fee that is paid is determined by the job poster. Selecting a job posting may comprise clicking on or otherwise entering an input signifying an intention to view the job.

Electronic job posting marketplace

A user submits a job search query in an online social networking system. The online social networking system calculates a score based on the similarity between the job search query and the profile of the user. When the score transgresses a threshold, the job search query is enhanced by adding data from the profile of the user to the job search query. The job search query is then used to search for, identify, and display jobs in the online social networking system.

Personalized job search and recommendations using job seeker behavioral features

Growing community of inventors

San Jose, CA, United States of America

Benjamin Hoan Le