Abstract: In some embodiments, a computer system generates a recommendation for a user of an online service based on user actions that have been performed by the user within a threshold amount of time before the generation of the recommendation. For each user action, the computer system determines an intent classification that identifies an activity of the user and that corresponds to different types of user actions, as well as a preference classification that identifies a target of the activity, and then stores these intent and preference classifications as part of indications of the user actions for use in generating different types of recommendations using different types of recommendation models. Additionally, the computer system may use mini-batches of data from an incoming stream of logged data to train an incremental update to one or more recommendation models.

Abstract: Techniques for implementing a feature generation pipeline for machine learning are provided. In one technique, multiple jobs are executed, each of which computes a different set of feature values for a different feature of multiple features associated with videos. A feature registry is stored that lists each of the multiple features. After the jobs are executed and the feature registry is stored, a model specification is received that indicates a set of features for a model. For each feature in a subset of the set of features, a location is identified in storage where a value for said each feature is found and the value for that feature is retrieved from the location. A feature vector is created that comprises, for each feature in the set of features, the value that corresponds to that feature. The feature vector is used to train the model or as input to the model.

Abstract: Techniques for improving the accuracy, relevancy, and efficiency of a computer system of an online service by providing a user interface to optimize a digital page of a user on the online service are disclosed herein. In some embodiments, a computer system receives a plurality of phrases for a type of job, selects a group of phrases from the plurality of phrases based on a corresponding relevancy measurement and a corresponding diversity measurement for each phrase in the selected group of phrases, and generates a recommendation for a page of a first user based on the selected group of phrases, with the recommendation comprising a suggested addition of the selected group of phrases to the page of the first user.

Abstract: Techniques for improving the accuracy, relevancy, and efficiency of a computer system of an online service by providing a user interface to optimize a digital page of a user on the online service are disclosed herein. In some embodiments, a computer system receives a plurality of phrases, and then, for each one of the plurality of phrases, selects a corresponding section of a page of a first user to suggest for placement of the phrase from amongst a plurality of sections using a placement classifier, and generates a corresponding recommendation for the page of a first user based on the phrase and the determined corresponding section of the page of the first user, with the recommendation comprising a suggested addition of the phrase to the determined corresponding section of the page of the first user.

Abstract: The video recommendation system provided with an on-line connection system generates on-line video recommendations using collaborative filtering for clusters of member profiles. The recommendation system clusters member profiles using member profile information as clustering criteria. The video recommendations are then generated for a given cluster, based on aggregation of video viewing history recorded for the member profiles that are in the given cluster, using the video similarity matrix. In order to produce video recommendations for a particular member profile, the recommendation system first determines cluster membership for the member profile, retrieves recommendations generated for that cluster, and provides recommendations to the associated member. A user interface including references to one or more recommended videos is rendered on a display device of a viewer.

Abstract: Techniques for improving the accuracy, relevancy, and efficiency of a computer system of an online service by providing a user interface to optimize a digital page of a user on the online service are disclosed herein. In some embodiments, a computer system identifies job postings published on an online service as corresponding to a type of job based on feature data of each one of the job postings, extracts phrases from the identified job postings based on a corresponding relevancy measurement and a corresponding diversity measurement for each one of the phrases, determines a corresponding section of a page of a user to suggest for placement of the extracted phrase using a placement classifier for each one of the extracted phrases, and generates a corresponding recommendation for the page based on the extracted phrase and the determined section of the extracted phrase for each one of the phrases.

Abstract: Techniques for improving the accuracy, relevancy, and efficiency of a computer system of an online service by providing a user interface to optimize a digital page of a user on the online service are disclosed herein. In some embodiments, a computer system receives a plurality of phrases, and then, for each one of the plurality of phrases, selects a corresponding section of a page of a first user to suggest for placement of the phrase from amongst a plurality of sections using a placement classifier, and generates a corresponding recommendation for the page of a first user based on the phrase and the determined corresponding section of the page of the first user, with the recommendation comprising a suggested addition of the phrase to the determined corresponding section of the page of the first user.

Abstract: Techniques for improving the accuracy, relevancy, and efficiency of a computer system of an online service by providing a user interface to optimize a digital page of a user on the online service are disclosed herein. In some embodiments, a computer system identifies job postings published on an online service as corresponding to a type of job based on feature data of each one of the job postings, extracts phrases from the identified job postings based on a corresponding relevancy measurement and a corresponding diversity measurement for each one of the phrases, determines a corresponding section of a page of a user to suggest for placement of the extracted phrase using a placement classifier for each one of the extracted phrases, and generates a corresponding recommendation for the page based on the extracted phrase and the determined section of the extracted phrase for each one of the phrases.

Abstract: Techniques for improving the accuracy, relevancy, and efficiency of a computer system of an online service by providing a user interface to optimize a digital page of a user on the online service are disclosed herein. In some embodiments, a computer system receives a plurality of phrases for a type of job, selects a group of phrases from the plurality of phrases based on a corresponding relevancy measurement and a corresponding diversity measurement for each phrase in the selected group of phrases, and generates a recommendation for a page of a first user based on the selected group of phrases, with the recommendation comprising a suggested addition of the selected group of phrases to the page of the first user.

Abstract: Techniques for improving the accuracy, relevancy, and efficiency of a computer system of an online service by providing a user interface to optimize a digital page of a user on the online service are disclosed herein. In some embodiments, a computer system receives a plurality of job postings published on an online service; determines that a subset of the plurality of the job postings satisfies a similarity criteria based on corresponding feature data of each job posting in the subset, selects the subset of the plurality of job postings based on the determining that the subset satisfies the similarity criteria, and generates a recommendation for a page of a first user based on the selected subset of job postings, the recommendation comprising a suggested addition of content to the page of the first user.

Abstract: A skills classification system is configured to calculate, for a skill from the skills database, industry-specific probabilities for the industries associated with the skill. An industry-specific probability for an industry with respect to a skill is the probability of that skill being a required skill for a job associated with that industry. The skills classification system also calculates an industry-agnostic probability with respect to that same skill, which is the probability of the skill being a required skills for any job regardless of the industry. Based on the distance between the set of industry-specific probabilities for the industries associated with the skill and the industry-agnostic probability, the skills classification system calculates a score for the skill. This score is used to determine whether the skill should be tagged with a soft skill identifier or a hard skill identifier.

Abstract: Techniques for improving the accuracy, relevancy, and efficiency of a computer system of an online service by providing a user interface to optimize a digital page of a user on the online service are disclosed herein. In some embodiments, a computer system accesses a profile of a first user of an online service stored in a database of the online service, and generates a suggestion for adding a measurable accomplishment to a particular section of a page of the first user based on profile data of the accessed profile using a neural network model, with the neural network model being configured to identify the measurable accomplishment based on the profile data of the accessed profile.

Abstract: Techniques for improving the accuracy, relevancy, and efficiency of a computer system of an online service by providing a user interface to optimize a digital page of a user on the online service are disclosed herein. In some embodiments, a computer system trains a classifier using a first plurality of training data, and then, for each one of a first plurality of sample data, generates a corresponding likelihood value indicating a likelihood that the one of the first plurality of sample data corresponds to a measurable accomplishment using the trained classifier, identifies a portion of the first plurality of sample data as corresponding to confused predictions based on the corresponding likelihood values of the portion of the first plurality of sample data and a confusion criteria, and retrains the trained classifier using a second plurality of training data that includes the portion of the first plurality of sample data.

Abstract: The recommendation system provided with an on-line connection system identifies on-line recommendations of videos and generates a user interface (UI) by including into the resulting presentation selected recommendations of videos. The recommendations of videos presented in the UI are organized into groups that are topically coherent, where each group is decorated with a context annotation—an explanation of why the recommendations in a given carousel are relevant for a member. Each video that is being evaluated by the recommendation system with respect to a subject member profile is assigned an annotation that is selected from a plurality of potentially applicable annotations.

Abstract: The video recommendation system provided with an on-line connection system generates on-line video recommendations using collaborative filtering for clusters of member profiles. The recommendation system clusters member profiles using member profile information as clustering criteria. The video recommendations are then generated for a given cluster, based on aggregation of video viewing history recorded for the member profiles that are in the given cluster, using the video similarity matrix. In order to produce video recommendations for a particular member profile, the recommendation system first determines cluster membership for the member profile, retrieves recommendations generated for that cluster, and provides recommendations to the associated member. A user interface including references to one or more recommended videos is rendered on a display device of a viewer.

Abstract: Techniques for implementing a feature generation pipeline for machine learning are provided. In one technique, multiple jobs are executed, each of which computes a different set of feature values for a different feature of multiple features associated with videos. A feature registry is stored that lists each of the multiple features. After the jobs are executed and the feature registry is stored, a model specification is received that indicates a set of features for a model. For each feature in a subset of the set of features, a location is identified in storage where a value for said each feature is found and the value for that feature is retrieved from the location. A feature vector is created that comprises, for each feature in the set of features, the value that corresponds to that feature. The feature vector is used to train the model or as input to the model.

Abstract: The recommendation system provided with an on-line connection system identifies on-line recommendations of videos and generates a user interface (UI) by including into the resulting presentation selected recommendations of videos. The recommendations of videos presented in the UI are organized into groups that are topically coherent, where each group is decorated with a context annotation—an explanation of why the recommendations in a given carousel are relevant for a member. Each video that is being evaluated by the recommendation system with respect to a subject member profile is assigned an annotation that is selected from a plurality of potentially applicable annotations.

Abstract: A system, a machine-readable storage medium storing instructions, and a computer-implemented method are described herein to a Discussion Relevance Engine that filters a plurality of discussions in a social network to identify a discussion pool. The Discussion Relevance Engine identifies a plurality of eligible discussions in the discussion pool, wherein each eligible discussion corresponds to a respective social network member group to which a target member account has previously subscribed. The Discussion Relevance Engine calculates, for each eligible discussion, a relevance score predictive of a relevance of the eligible discussion to the target member account. The Discussion Relevance Engine recommends at least one of the eligible discussions to the target member account based at least in part on the calculated relevance scores.

Abstract: A system, a machine-readable storage medium storing instructions, and a computer-implemented method are directed to a Digest Engine that identifies a feature(s) that is predictive of relevance, to a target member account in a professional social network, of content from a member group(s) to which the target member account is subscribed. Based on the feature(s), the Digest Engine determines a portion(s) of relevant content created amongst respective member accounts subscribed to the member group(s). The Digest Engine generates a persistent message providing access to the portion(s) of relevant content. The Digest Engine sends the persistent message to the target member account.