Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: The disclosed embodiments provide a system for processing data. During operation, the system obtains feature configurations for a set of features. Next, the system obtains, from the feature configurations, an anchor containing metadata for accessing a first feature in an environment and a feature derivation for generating a second feature from the first feature. The system then uses the anchor to retrieve feature values of the first feature from the environment and uses the feature derivation to generate additional feature values of the second feature from the feature values of the first feature. Finally, the system provides the additional feature values for use with one or more machine learning models.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: A system, a machine-readable storage medium storing instructions, and a computer-implemented method are described herein are directed to a Jobs Optimization Engine. The Jobs Optimization Engine accesses at least one respective apply probability that corresponds to a given job post from a plurality of job posts, each respective apply probability represents a likelihood that the target member account will apply to the given job post. The Jobs Optimization Engine determines, according to an input context and the at least one respective apply probability, a respective boost factor for each given job post based on including the given job post in a select listing of job posts that satisfies (i) a job post diversity requirement and (ii) a potential revenue target that can be generated by the select listing of job posts.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: An online social networking system receives a job search query from a member, and retrieves job postings from a database. The system applies a first scoring model to the retrieved job postings, thereby generating a first coarse ranking of the retrieved job postings. The system then identifies a top percentage or number of job postings from the first coarse ranking, and applies a second scoring model to the top percentage or number of job postings, thereby generating a second fine ranking of the retrieved job postings. The system then displays the second fine ranking of the retrieved job postings on a computer display device.

Abstract: A system calculates an overall talent scout score for each of a plurality of interviewers, ranks the plurality of interviewers as a function of the overall talent scout score for each of the plurality of interviewers, and displays on a computer display device a representation of the overall talent scout scores for each of the plurality of interviewers. In another embodiment, the system calculates a participation score for each of the plurality of interviewers, ranks the plurality of interviewers as a function of the overall talent scout score for each of the plurality of interviewers and the participation score for each of the plurality of interviewers, and displays on a computer display device a representation of the overall talent scout scores and the participation scores for each of the plurality of interviewers.