Abstract: A member profile including a vector containing a field for each of a plurality of skills and a rating of one or more of the skills in the vector for a member of a social networking service is obtained. A first distance indicating a vector distance between the vector of the member profile and a vector of a hypothetical member profile representing the perfect job candidate is obtained. A hypothetical member profile for the member is created by combining the vector of the member profile with the indication of how each of the one or more skills is improved through taking the course from course information. A second distance between the member and the hypothetical perfect candidate for the job is obtained, and the difference between the first distance and the second distance is calculated to determine an estimate of how much the course will increase the member's job chances.

Abstract: Methods and systems for generating queries from a behavioral index model are described. According to various embodiments, a system receives a query input including one or more search terms from a client device associated with a member profile. The system generates a query from the one or more search terms and one or more profile terms. The system causes one or more query machines to search one or more inverted indices using the query and receives one or more result of documents distributed across the inverted indices. The system generates an ordered list of the one or more result sets and causes presentation of the ordered list at a client device associated with the member profile.

Abstract: A machine may be configured to generate a universal concept graph. For example, the machine generates an internal set of concept phrases based on an internal dataset including content from internal documents associated with a social networking service (SNS). The machine generates an external set of concept phrases based on an external dataset including content from external documents that are external to the SNS. The machine generates a set of nodes for a universal concept graph based on performing a union operation of the internal set of concept phrases and the external set of concept phrases. Each node corresponds to a particular concept phrase. The machine generates a set of edges among a plurality of nodes of the set of nodes based on one or more relationship indicators for pairs of nodes. The machine generates the universal concept graph based on the set of nodes and the set of edges.

Abstract: A machine may be configured to determining key concepts in documents. For example, the machine accesses a universal concept graph that includes a first set of nodes that represent concept phrases derived from internal documents associated with a social networking service (SNS) and external documents that are external to the SNS, and a first set of edges that connect a plurality of nodes of the first set of nodes. The machine accesses a content object associated with the SNS. The machine generates an induced concept graph associated with the content object based on an analysis of the content object and the universal concept graph. The machine identifies one or more key concept phrases in the content object based on applying one or more key concept selection algorithms to the induced concept graph. The machine stores the one or more key concept phrases in a record of a database.

Abstract: A machine may be configured to identify top jobs for a member of a social networking service (SNS) based on a universal concept graph. For example, the machine accesses a first record that identifies a universal concept graph. The machine accesses a second record that identifies a first induced concept graph associated with a member profile of a member of the SNS. The machine identifies a numerical value that represents a desired number of job descriptions. The machine generates, for a job description, a similarity value based on the first induced concept graph and a second induced concept graph associated with the job description. The similarity value represents a degree of similarity between the member profile and the job description. The machine causes a presentation of identifiers of job descriptions in a user interface based on the numerical value and the similarity values associated with the identifiers of job descriptions.

Abstract: A machine may be configured to identify top members of a social networking service (SNS) for a job based on a universal concept graph. For example, the machine accesses a first record that identifies a universal concept graph. The machine accesses a second record that identifies a first induced concept graph associated with a job description. The machine identifies a numerical value that represents a desired number of member profiles. The machine generates, for a member profile, a similarity value based on the first induced concept graph, and a second induced concept graph associated with the member profile. The similarity value represents a degree of similarity between the job description and the member profile. The machine causes a presentation of identifiers of member profiles in a user interface of a client device based on the numerical value and the similarity values associated with the identifiers of the member profiles.

Abstract: Methods and systems for generating and storing entity chain information, and for responding to search queries according to the entity chain information is presented. As a service obtains information regarding geographic entities, a plurality of entity records corresponding to each of a plurality of geographic entities is created (or updated) in an entity store. The service then analyzes the plurality of geographic entities (via the entity information in each of the entity records) to identify geographic entities that belong to an entity chain. Information regarding the identified entity chains are then also stored in the entity store.

Abstract: An on-line social network system includes or is in communication with a recommendation system that is configured to assign jobs to members while taking into account the relevance of a job for a given member as well as the relevance of the same job for other members. The objective of said optimization is to maximize the total sum of respective relevance scores generated for member/job pairs for jobs that get selected for presentation to members. The optimization objective is constrained by the maximum number of job recommendations desirable for each member profile and may also be constrained by the maximum number of member recommendations desirable for each job posting.

Abstract: An on-line social network system includes or is in communication with a recommendation system that is configured to assign members to jobs while taking into account fitness of a member for the job, as well as the relevance of that job for that given member, as well as the relevance of the same job for other members. The objective of said optimization is to maximize the total sum of respective relevance scores generated for member/job pairs for members that get selected for presentation to posters of jobs. The optimization objective is constrained by the maximum number of job recommendations desirable for each member profile and may also be constrained by the maximum number of member recommendations desirable for each job posting.

Abstract: A system, a computer-readable medium comprising instructions, and a computer-implemented method are directed to a Forecasting Engine, as described herein. The Forecasting Engine receives a ranked list of content portions that are ranked based on relevance score values of the content portions. Each relevance score value is indicative of a measure of similarity between a member account of a social network service and a content portion. The Forecasting Engine forecasts an expected number of member account actions resulting from presentation of a content portion included in the ranked list to a member account. The Forecasting Engine modifies the relevance score value of the content portion based on the expected number of member account actions. The Forecasting Engine updates the ranked list based on a modified relevance score value of the content portion. The Forecasting Engine generates and causes a display of a user interface that presents the updated ranked list.

Abstract: A machine may be configured to determining key concepts in documents. For example, the machine accesses a universal concept graph that includes a first set of nodes that represent concept phrases derived from internal documents associated with a social networking service (SNS) and external documents that are external to the SNS, and a first set of edges that connect a plurality of nodes of the first set of nodes. The machine accesses a content object associated with the SNS. The machine generates an induced concept graph associated with the content object based on an analysis of the content object and the universal concept graph. The machine identifies one or more key concept phrases in the content object based on applying one or more key concept selection algorithms to the induced concept graph. The machine stores the one or more key concept phrases in a record of a database.

Abstract: A machine may be configured to generate a universal concept graph. For example, the machine generates an internal set of concept phrases based on an internal dataset including content from internal documents associated with a social networking service (SNS). The machine generates an external set of concept phrases based on an external dataset including content from external documents that are external to the SNS. The machine generates a set of nodes for a universal concept graph based on performing a union operation of the internal set of concept phrases and the external set of concept phrases. Each node corresponds to a particular concept phrase. The machine generates a set of edges among a plurality of nodes of the set of nodes based on one or more relationship indicators for pairs of nodes. The machine generates the universal concept graph based on the set of nodes and the set of edges.

Abstract: Methods and systems for developing a behavioral index model are described. According to various embodiments, the system accesses a set of behavioral data stored in association with a set of member profiles. The system generates a set of training data from the set of behavioral data and generates a set of feature vectors from the set of training data. The system generates a behavioral index model from the set of training data and the set of feature vectors. The system then generates a tuned behavioral index model from the behavioral index model by tuning a threshold of the behavioral index model using a precision recall curve.

Abstract: Methods and systems for generating queries from a behavioral index model are described. According to various embodiments, a system receives a query input including one or more search terms from a client device associated with a member profile. The system generates a query from the one or more search terms and one or more profile terms. The system causes one or more query machines to search one or more inverted indices using the query and receives one or more result of documents distributed across the inverted indices. The system generates an ordered list of the one or more result sets and causes presentation of the ordered list at a client device associated with the member profile.

Abstract: In an example embodiment, a method is provided where information regarding a member of a social networking service and a job opening are obtained. Then information about a plurality of courses available for the member to take is obtained, the information including cost, time, and a vector including, for each of a plurality of skills identified in a member profile of the member, an effect of taking the corresponding course. A subset selection algorithm is then used to select an optimal combination of courses selected from the plurality of courses, based on minimizing cost and time while maximizing cumulative increase in odds of the member successfully obtaining the job opening from taking the selected courses.

Abstract: In an example embodiment, a method is provided to calculate a distance for a first member of a social networking service and a job opening, which indicates the likelihood that the first member will obtain the job. The distance is calculated by applying one or more policies to member profiles of members who applied for similar jobs to obtain a hypothetical perfect candidate for the job. The member's profile is then automatically compared to the hypothetical perfect candidate profile to calculate the distance.

Abstract: A member profile including a vector containing a field for each of a plurality of skills and a rating of one or more of the skills in the vector for a member of a social networking service is obtained. A first distance indicating a vector distance between the vector of the member profile and a vector of a hypothetical member profile representing the perfect job candidate is obtained. A hypothetical member profile for the member is created by combining the vector of the member profile with the indication of how each of the one or more skills is improved through taking the course from course information. A second distance between the member and the hypothetical perfect candidate for the job is obtained, and the difference between the first distance and the second distance is calculated to determine an estimate of how much the course will increase the member's job chances.

Abstract: Methods and systems for generating and storing entity chain information, and for responding to search queries according to the entity chain information is presented. As a service obtains information regarding geographic entities, a plurality of entity records corresponding to each of a plurality of geographic entities is created (or updated) in an entity store. The service then analyzes the plurality of geographic entities (via the entity information in each of the entity records) to identify geographic entities that belong to an entity chain. Information regarding the identified entity chains are then also stored in the entity store.

Abstract: The subject disclosure is directed towards building one or more context and query models representative of users' search interests based on their logged interaction behaviors (context) preceding search queries. The models are combined into an intent model by learning an optimal combination (e.g., relative weight) for combining the context model with a query model for a query. The resultant intent model may be used to perform a query-related task, such as to rank or re-rank online search results, predict future interests, select advertisements, and so forth.