ABSTRACT
The act of seeking employment is a two-way choice between the job seeker and the recruiter. Traditional job search models are mostly qualitative judgments based on the recruiter's perceptual preferences, which are highly random, subjective, and potentially unfair. Developing an internet-active big data job dual selection model is necessary. We aim to construct its grassroots logic, boil down the extensive data nature of job seekers and recruiters to universal multi-level indicators, apply mathematical methods for fuzzy quantification and comprehensive scoring, explore their stable patterns with matching theory, and form a model framework that can use in intelligent matching web platforms involving headhunting, job search, luxury goods, and other dual selection.
