Automatisk jobbmatchning

Abstract

In order to facilitate the workflow of recruiters who work daily with finding suitable assignments for their consultants, a system was created that can automatically match these consultants against different job listings. Creating such a system was a complex task since job listings often consist of unstructured text which is difficult to interpret for a computer. To deal with this problem, Natural Language Processing was applied, which is a methodology for managing unstructured text using artificial intelligence and various algorithms. The completed system delivered several positive results, in addition to these some misleading ones were also produced. The system’s results are recommended to be used as guidelines to pursue for a recruiter when a suitable candidate is to be selected for an assignment. There is much room for development to improve the system’s reliability and to reduce the likelihood of misleading results.