Modelling Student Employability on an Academic Basis

Abstract

With the population growth and the employability scarcity, the placement of students has become a significant concern. Problems of global ageing and miss-match of student skill and knowledge can be witnessed easily. Fewer works of literature are available to predict the placement of students. This study aims to create a supervised machine learning (SML) model to predict the employability of graduates based on their academic scores and streams. The study used the decision-tree technique to create the SML model. The model can predict the placement chance based on students' academic scores and streams with 65% accuracy. Some new theoretical and practical contributions have been discussed.