An Empirical Study - The Cardinal Factors towards Recruitment of Faculty in Higher Educational Institutions using Machine Learning

Abstract

Teaching Job Performance is one of the salient and sensitive issues when it is associated with the recruitment and deployment of faculty for Higher Education Institutions. Recruiting effective faculty contributes to the growth and enhancement in the quality of education. Considering this, the study unveils the importance of four cardinal factors on a real dataset sample of 520 faculty, from different departments of Indian Institutes. Cardinal factors such as Faculty’s Experience, National Eligibility Test, Student Feedback, and Faculty’s Highest Qualification are taken into consideration. The classifiers used to strengthen research are Logistic Regression, Support Vector Machine, K-Nearest Neighbors, and Decision Tree. The results prove that the correlation between Faculty’s Experience, Faculty’s Highest Qualification with Student Feedback is the best way to analyze a Faculty's Teaching Performance. Analyzing and predicting the importance of four cardinal parameters will help educational institutions, regulatory and accreditation bodies improve education quality.