Lazy Learned Screening for Efficient Recruitment - A Candidate Ranking System using Case Based Reasoning and Semantic Data Models

Abstract

The transition from traditional paper based systems for recruitment over to the internet has resulted companies in getting a lot more applications. A majority of these applications are often unstructured documents sent over mail. This results in a lot of work sorting through the applicants. Due to this, a number of systems have been implemented in an effort to make the screening phase more efficient. The main problems consisting of extracting information from resumes and ranking the candidates the candidates for positions based on their relevance.

In this research we want to develop a system that can learn how to rank candidates for a position based on knowledge obtained from earlier screening phases. To this end we developed and integrated a Candidate Ranking System based on a lazy learning technique, namely Case Based Reasoning, combined with semantic data models. The systems performance was evaluated in conjunction with having Okapi BM25 as a baseline due to its widespread usage in comparing ranking system and other related work.