A COMPREHENSIVE EVALUATION OF EMPLOYABILITY PREDICTION USING ENSEMBLE LEARNING TECHNIQUES

Abstract

The Quality Education plan reflected in the Goal four of the United Nations 2030 Agenda for Sustainable Development stresses the essential function of Education in developing an equitable and just society and reaching complete human potential. The present-day Technical Higher Education system focuses only on the skill sets a student acquires on completion of the programme. The visibility of private HEI is made through the national and international rankings they have and the stakeholders are concerned about the campus placements of their wards. The IT firms chooses HEI s for campus drives by their visibility and they need skilled workforce with multidisciplinary abilities. This study by collecting information from the student database, employing ensemble learning techniques, focuses on such aspects makes an efficient prediction on factors that contribute to high quality learning and improved possibility of campus placement. The proposed model extracts data from dataset with 20 attributes. This enhanced predictive approach based on stacking ensemble learning approach predicts the campus placement chances to an accuracy of 90.21%.