Examining Graduates' Job-Readiness, Employability Skills, and Awareness using machine learning

Abstract

The importance of higher education institutions (HEIs) understanding the employability of their graduates and the reasons behind it is growing as the number of graduates produced annually from HEIs continues to rise and competition for good jobs heats up. One performance indicator for HEIs is the employability of its graduates. Because it is often used as a measure of success, student employability is vital for educational institutions. On the other hand, globalization, automation, and the latest developments in AI are making the labour market environment more dynamic than ever before. Prior to graduation, students' employability was predicted using machine learning models. Logistic regression, decision trees, random forests, and the K-Means method are all part of this category. Therefore, the purpose of this study is to forecast undergraduates' full-time employability using academic and experience employability attributes, such as CGPA, SIWES, extracurricular activities, gender, and union affiliations prior to graduation.