Abstract: Disclosed are systems, methods, and non-transitory computer-readable media for expanding search queries. A search system determines a set of candidate alternate search terms based on historical search logs that include records of previously submitted search terms, corresponding search results that were presented to users, and corresponding search results that were selected by the users. The set of candidate alternate search terms is selected from titles of the corresponding search results that were selected by the users. The search system ranks the set of candidate alternate search terms based on determined probabilities that each of the alternate candidate search terms will be selected if presented to a user, and selects a first candidate alternate search term from the set of candidate alternate search terms based on the ranking. The search system generates an expanded search term based on the first candidate alternate search term.

Abstract: A system filters profiles of an online business network as a function of recent college graduates who have recently become employed in first employment positions, and identifies codes associated with the first employment positions. The system filters job listings using the identified codes to identify job listings that are closed and similar to the first employment positions. The system stores the identified job listings that are similar to the first employment positions into a first subset of job listings, and analyzes the job descriptions in the first subset of job listings using a logistic regression to model job listings with predictor variables indicating whether the requirements expressed in the job descriptions—for example, requirements of previous work experience—are likely optional or mandatory.

Abstract: Systems and methods for managing overlapping taxonomies, in accordance with some embodiments, are disclosed. The system stories a set of taxonomic grouping rules for organizing members based on stored member data and receives a request for grouping information for a particular member. Using stored member data for the particular member, the system classifies the particular member into an atomic taxonomic group in the plurality of the atomic taxonomic groups. The system, based on the atomic taxonomic group that the particular member is classified into, automatically determines the requested grouping information. The system then transmits the requested grouping information to a requesting computer system.

Abstract: Network insights are bite-sized pieces of information about member's connections in the on-line social network that contain information that may be of interest to a viewing member but that is difficult or time-consuming to find. A network insights system generates and stores insights for each member in an on-line social network system. A network insights system also generates a set of personalization features for each member profile in the on-line social network. A set of personalization features for a member profile reflects the relevance of each possible value of a certain profile attribute with respect to the member profile. When a network insights system determines that a member (the viewer) is to be presented with one or more insights with respect to another member (the viewee) it selects insights of the viewee for presentation to the viewer based on the set of personalization features for the viewer.

Abstract: Method and system to determine a school rank utilizing on-line social network data is described. A school ranking system may be configured to determine a ranking of a school based on career outcomes data which may be Obtained from member profile data stored by an on-line social network system. The school ranking system may examine the member profiles and determine how many of the target school alumni can be considered successful alumni and then calculate a success score for a school as a number of successful alumni divided by the total number of the school's alumni.

Abstract: Method and system to determine a company rank utilizing on-line social network data is described. A company ranking system may examine member profiles representing respective members of an on-line social network system and extract transition data. From the transition data, the company ranking system may construct a company transition graph having nodes that represent respective companies and edges that represent transitions of employees from one company to another. A rank or a node score for each node of the company transition graph may be determined by applying a ranking algorithm to the graph. The scores generated for respective nodes in the company transition graph may be stored for future use in a database.

Abstract: A machine may be configured to identify skills for a projected next job position. For example, the machine performs an analysis of profile data associated with a plurality of members of a social network service. Based on the analysis of the profile data and a present job position of a particular member of the social network service, the machine identifies a projected next position in a career path model. The machine identifies a cohort of other members of the social network service. The identifying of the cohort may be based on each cohort member holding the projected next position in a respective career. Each cohort member may be associated with one or more skills. The machine identifies one or more over-indexed skills for the cohort based on the one or more skills of the cohort members. The machine generates a recommendation that includes the one or more over-indexed skills.