Predicting the suitability of IS students’ skills for the recruitment in Saudi Arabian industry

Abstract

Soft and hard skills have become a challenging issue for Information Systems (IS) graduates and recruiters in Saudi industry. IS students are lacking the skills that are required by Saudi industry. Recruiters, on the other hand, consider the GPA as a major factor for hiring IS candidates. This paper discusses the impacts of self-regulated learning strategies and academic achievements on matching the required skills of Saudi industry. Therefore, it identifies the most required skills of IS jobs in Saudi industry and how the skills of IS students in major Saudi universities can match them. Two questionnaires were distributed, one for recruiters and another for students. First questionnaire is to assess the required IS skills in Saudi industry by recruiters. Second questionnaire is to capture the skills, self-regulated learning (SRL), and academic achievement of IS students. The collected data was used to develop a classification model using Decision Tree, Naïve Bayes, and Nearest Neighbor algorithms to predict the suitability of IS graduates to the Saudi industry. The results show that the Naïve Bayes algorithm performed the best (with accuracy 69% and ROC 0.62). Finally, this paper demonstrated a novel way to predict student skills’ suitability for the industry and thereby helping the universities to design better curriculum and the students to prepare better for the job market.