Effort Estimation Using Hybridized Machine Learning Techniques for Evaluating Student’s Academic Performance

Abstract

Machine Learning (ML) Technology is an area of Artificial Intelligence (AI) to facilitate computer systems with the capability to involuntarily learn and improve from user experience without being explicitly programmed from outside. It mainly focuses on the expansion of computer programs that can access data from its user to learn for themselves. With this technology, we can predict the performance of the student in academic. Here, we are implemented Naive-Bayes (NB), Support Vector Machine (SVM), Random Forest (RF) and Artificial Neural Network (ANN) algorithms to find the total effort required for analysis. We proposed a Hybridized Support Vector Machine-Neural Network (SVM-NN) Machine Learning Algorithm which requires less effort to accurately analysis the student's academic performance.