Abstract: In an example embodiment, a plurality of member profiles in a social networking service are obtained, each member profile identifying a member and listing one or more skills the corresponding member has explicitly added to the member profile, the one or more skills indicating a proficiency by the member in the corresponding skill. A members-skills matrix is formed with members on one axis of the matrix and skills on another axis of the matrix, wherein each cell in the matrix is assigned a first value if the corresponding member explicitly lists the corresponding skill in the corresponding member profile and a second value if the corresponding member does not explicitly list the corresponding skill in the corresponding member profile. The members-skills matrix is factorized into a members matrix and a skills matrix in k-dimensional latent space, and then the dot product of the members matrix and the skills matrix is computed.

Abstract: System and techniques for facet expansion are described herein. A user interface element may be presented on facet selection portion of a search result display including search results. Here, the user interface element is arranged to accept user input of a facet. Partial user input for a facet may be received. A peer entity to an entity corresponding to the facet may be obtained. A peer facet may be presented in a suggestion element in the facet selection portion in response to receiving the partial user input.

Abstract: System and techniques for autonomously adaptive performance monitoring are described herein. A text input field may be presented on a graphical user interface. A flow-selector may be presented in contact with the text input field in response to receiving user input at the text input field. Here, the flow-selector includes a set of flow choices selected based on the user input. A user selection of a flow choice may be received. Next-steps flow elements may be presented in response to the user selection. User query choices may be collected from the next-steps flow elements to populate a query template corresponding to the flow choice. The query template is executed to produce search results.

Abstract: Techniques for improving search relevance using past searchers' reputation are described. According to various embodiments, a specification of a search query term corresponding to a skill is received from a searcher; in connection with a search for members of an online social networking service having the skill. Thereafter, a list of search results is generated and displayed based on the search query term, each of the search results corresponding to a member of the online social networking service. A subsequent interaction between the searcher and a specific member corresponding to one of the search results is detected. A skill reputation score associated with the searcher and the skill is then accessed. Thereafter, a search relevance score associated with the specific member and the skill is modified based on the skill reputation score associated with the searcher and the skill.

Abstract: Apparatuses, computer readable medium, and methods are disclosed for federated search page construction based on machine learning. The method may include receiving a search query submitted by a searcher and submitting the search query to a plurality of sources of information to generate a plurality of search results. The method may further include ranking the plurality of search results based on historical search data and selecting a primary search result and a secondary search result of the plurality of search results based on the ranking. The method may further include constructing a federated search results page with a first portion of the first search results positioned first, a cluster of the second search result positioned second, and a second portion of the first search results positioned third. The method may include causing the federated search results page to be displayed to the searcher.

Abstract: Techniques for estimating, in real time, the likelihood that any particular member of a social network service is a third degree connection of another member are described. Consistent with some embodiments, various member profile attributes of a member are used as a sort of proxy for determining the likelihood or probability that the member is a third degree connection of another member. For example, in some instances, the number of first-degree connections a member has is used to derive a probability score indicating the likelihood that the member is a third-degree connection of another member, such as a person performing a people-search. Once derived, the probability score for each member may be used in various applications, such as a people-search engine, to boost or increase a ranking score assigned to each search result and used to order the search results when presented to the user who has performed the search.

Abstract: Techniques for assisting a user in conducting an online job search for online job listings are described. According to various embodiments, a user specification of a job search query including at least one user-specified job search query term is received. Values for one or more member profile attributes of the user are then accessed. Thereafter, the job search query is modified based on the accessed values for the member profile attributes of the user, the modifying comprising inserting job search query terms corresponding to the values for the member profile attributes into the job search query. Search results corresponding to job listings posted on the job search engine are then generated, based on the modified job search query. Further, one or more of the search results may be displayed, via a user interface.

Abstract: Disclosed in some examples are methods, systems, and machine-readable mediums which provide for a personalized expertise searching. When a user of the social networking service enters a search query, the system determines if the user is searching for members who possess a particular skill. If the user is searching for members who possess a particular skill, the search results are post-processed by personalizing the search results using one or more machine-learning models which utilize one or more observed features about the user that enters the query, the skills of the members of the social networking service, and the query itself. In some examples, the system may utilize multiple machine-learning models in multiple passes to fine tune the relevance of the search results and to ensure that the post-processing returns search results in a timely manner.

Abstract: A system and method for personalized search user searcher features may include obtaining a search term from a member of a social network at a user device via the network interface. An initial result may be generated based on the search term, including a first group of content items from a social network and stored in a content database, the content items including member profiles of members of the social network. Each of the content items of the first group may be ranked based on information indicative of interactions from an activity database with the content items of the first group, the interactions being by at least a second user of the social network different than the first user. A second group of the content items may be displayed, including at least some of the first group of the content items, based on the rank of the first group of the content items.

Abstract: A system and method for personalized search based on searcher interest may include obtaining a search term from a member of a social network at a user device via the network interface. An initial result may be generated based on the search term, including a first group of content items from a social network and stored in a content database, the content items including member profiles of members of the social network. Each of the content items of the first group may be ranked based on information from an activity database, the activity database storing the information related to the social network, the activities including interactions with search results that include ones of the member profiles. A second group of the content items may be displayed, including at least some of the first group of the content items, based on the rank of the first group of the content items.

Abstract: A system and method for personalized search based on similarity may include obtaining a search term. An initial result based on the search term and including a first group of content items as stored in a content database may be generated. Each of the content items of the first group may be ranked based, at least in part, on similarity scores, each of the similarity scores individually based on a first member profile relative to individual ones of second member profiles to which an activity related to a content item of the first group corresponds. The user device may display a second group of the content items, including at least some of the first group of the content items, according to the rank of the first group of the content items.

Abstract: Systems and methods for searching for information within social networks are described. In some examples embodiments, a search assist system receives a query, such as a partial query, identifies two or more categories of data that include information satisfying the query, ranks the identified categories of data based on various selection criteria, and presents suggested search terms based on the rankings.

Abstract: Techniques for optimizing non-convex function for learning to rank are described. Consistent with some embodiments, a search module may set an order for a group of search features. The group of search features can be used by a ranking model to determine the relevance of items in a search query. Additionally, the search module can assign a first weight factor to a first search feature in the group of search features. Moreover, the search module can calculate a mean reciprocal rank for the search query based on the assigned first weight factor. Furthermore, the search module can determine a second weight factor, using a preset incremental vector, for a second search feature in the group of search features to maximize the mean reciprocal rank for the search query. Subsequently, the search module can assign the second weight factor to the second search feature in the group of search features.

Abstract: A system includes a database, a network interface, and a processor. The database includes, for each multiple users of a social network, profile data and activities, by the user, related to the social network. The network interface is configured to be communicatively coupled to user devices associated with the population of users. The processor is configured to obtain a recruitment search query for a position in an organization, compare the recruitment search query against the profile data of at least some of the users to obtain a comparison, determine, for each of the at least some of the users, a likelihood of interacting with a recruiter associated with the position based on the activities of each of the at least some of the users, and transmit, to at least one of the users, a communication related to the position based, at least in part, on the comparison and the likelihood of interacting.

Abstract: Disclosed in some examples are methods, systems, and machine readable mediums which find a special set of keywords which, when used to search a supplemental set of search verticals (e.g., the newly added search verticals), return high quality results. When a user enters a search containing one or more keywords from the special set of keywords, the system may search both the standard set of search verticals (as normal), but also the one or more keywords may be used to search the supplemental set of search verticals. Results from both may then be presented to the user.

Abstract: Systems and methods for searching for information within social networks are described. In some examples embodiments, a search assist system receives a query, such as a partial query, identifies two or more categories of data that include information satisfying the query, ranks the identified categories of data based on various selection criteria, and presents suggested search terms based on the rankings.

Abstract: Systems and methods for searching for information within social networks are described. In some examples embodiments, a search assist system receives a query, such as a partial query, identifies two or more categories of data that include information satisfying the query, ranks the identified categories of data based on various selection criteria, and presents suggested search terms based on the rankings.

Abstract: Techniques for ranking search results generated by a search engine are described. Consistent with some embodiments, a search engine processes a search query to identify member profiles of members of a social network service for presentation in a search results page or user interface. The member profiles are presented in the search results ordered based on a ranking score that is derived at least in part by identifying similarities in the member profile attributes of the member profiles satisfying the search query and the member profile of the person performing the search. Accordingly, to the extent that a member profile has similarities shared in common with the member profile of the member performing the search, that member profile is more likely to be presented more prominently in the search results.

Abstract: Techniques for estimating, in real time, the likelihood that any particular member of a social network service is a third degree connection of another member are described. Consistent with some embodiments, various member profile attributes of a member are used as a sort of proxy for determining the likelihood or probability that the member is a third degree connection of another member. For example, in some instances, the number of first-degree connections a member has is used to derive a probability score indicating the likelihood that the member is a third-degree connection of another member, such as a person performing a people-search. Once derived, the probability score for each member may be used in various applications, such as a people-search engine, to boost or increase a ranking score assigned to each search result and used to order the search results when presented to the user who has performed the search.