Problem being addressed
One of the goals of LinkedIn is to create economic opportunity for everyone in the global workforce. A critical aspect of this goal is matching jobs with qualified applicants.
To improve hiring efficiency and reduce the need to manually screening each applicant, the researchers develop a new product where recruiters can ask screening questions online so that they can filter qualified candidates easily. To add screening questions to all 20M active jobs at LinkedIn, they propose a new task that aims to automatically generate screening questions for a given job posting. To solve the task of generating screening questions, they develop a two-stage deep learning model, where they apply a deep learning model to detect intent from the text description, and then rank the detected intents by their importance based on other contextual features. Since this is a new product with no historical data, they employ deep transfer learning to train complex models with limited training data.
Advantages of this solution
The online A/B test demonstrated +53.10% screening question suggestion acceptance rate, +22.17% job coverage, +190% recruiter-applicant interaction, and +11 Net Promoter Score. In sum, the deployed model helps recruiters to find qualified applicants and job seekers to find jobs they are qualified for.
Solution originally applied in these industries
Possible New Application of the Work
The models that optimize screening questions can be successfully used during the enrolling process to better select the students whose profiles match selected disciplines.
Hiring influencers for different social media campaigns can be quite expensive and selecting the right candidate can be significantly improved with the matching algorithm that identifies the right candidate qualities.
Source URL: #############