Automatic matching of job offers and job candidates is a major problem for anumber of organizations and job applicants that if it were successfullyaddressed could have a positive impact in many countries around the world. Inthis context, it is widely accepted that semi-automatic matching algorithmsbetween job and candidate profiles would provide a vital technology for makingthe recruitment processes faster, more accurate and transparent. In this work,we present our research towards achieving a realistic matching approach forsatisfactorily addressing this challenge. This novel approach relies on amatching learning solution aiming to learn from past solved cases in order toaccurately predict the results in new situations. An empirical study shows usthat our approach is able to beat solutions with no learning capabilities by awide margin.
展开▼
