Abstract
Recruitment of graduates depends on the quality of skills that a graduate may have gained during their study. Hence, the quality of education and ensuring that graduates have sufficient knowledge about the in-demand skills of the technological sector are necessary. However, IT graduates are usually not aware whether they are suitable for recruitment or not. This study builds a prediction model that can be deployed on the web, where graduates can input variables to generate predictions. Furthermore, this study provides data-driven recommendations of the in-demand skills in the technological sector in Saudi Arabia to overcome the unemployment problem. The data were collected from two online job portals: LinkedIn and Bayt.com. Three machine learning algorithms, namely, Support Vector machine (SVM), k-Nearest Neighbor, and Naive Bayes were used to build the prediction model. Furthermore, descriptive and data analysis methods were employed herein to evaluate the existing gap. IT graduates in Saudi Arabia were surveyed unto whether or not they hold the required skills obtained from our analysis of the online job portals. Results showed that there existed a gap between employers' expectations of graduates and the skills that the graduates were equipped with from their educational institutions. Also, the result explains that the educational output has been improved over the past years, particularly in soft skills. Planned collaboration between industry and education providers is required to narrow down this gap. The implications of this study are beneficial for the academia to better align their educational programs with the advancement in the technological sector.