Machine Learning-based Model to Predict Student's success in Higher Education

Abstract

. Predictions are always helpful for making decisions. Students are the future of the world. Higher Education Institutions (HEI's) in developing countries cannot apply similar strategies to all the students. Academic achievement plays a crucial role in the academic system because it is often utilized for the educational establishment quality. Early identification of at-risk educators and prevention strategies can significantly improve their chances of succeeding. Education is affected by different environments, family backgrounds, social and personal responsibilities. In this research article student's performance is measured based on various parameters using Random Forest, Naive Bayes and K* method. Experimental analysis shows the strengthening of the random forest method over K* and Naive Bayes method.