How does 'Bright score' assess how strong the connection is between users and their jobs?

Question

In 2014 Linkedin acquired Bright.com, for $120 million and it is using AI and big data algorithms to connect users.

Bright also throws in a little Klout, ranking people by a “Bright score” which it uses to assess how strong the chemistry is between a user and a particular job.

It also takes into account historical hiring patterns into its matching, along with account location, a user’s past experience and synonyms.

In brief, is it known (based on some research papers) how such algorithm works which aiming at scoring 'chemistry' between users and their jobs?

Answer 1

Take a look at this 2012 paper by three people at Bright. (Sadly, it's paywalled and I couldn't easily find a ungated copy, so I don't have a summary for you.)

The abstract:

Bright has built an automated system for ranking job candidates against job descriptions. The candidate's resume and social media profiles are interwoven to build an augmented user profile. Similarly, the job description is augmented by external databases and user-generated content to build an enhanced job profile. These augmented user and job profiles are then analyzed in order to develop numerical overlap features each with strong discriminating power, and in sum with maximal coverage. The resulting feature scores are then combined into a single Bright Score using a custom algorithm, where the feature weights are derived from a nation-wide and controlled study in which we collected a large sample of human judgments on real resume-job pairings. We demonstrate that the addition of social media profile data and external data improves the classification accuracy dramatically in terms of identifying the most qualified candidates.