Track: Data Analytics and Big Data

Abstract

Analyzing students’ performances based on both subjective and quantitative components is fundamental because sometimes these performances and so many other factors have led students to quit their studies or be dropped out of the institutions. This dropout rate is much higher in undergrad students than other educational stages. The first-year result of a student is very vital since within the larger part of cases this drives them to be either inspired or demotivated. So, the second-year result of an eminent university in Bangladesh is examined in this paper. This paper is basically based on finding the factors for students’ distinctive sorts of performances and after that predicting students’ results based on those six noteworthy variables. For this reason, support vector machines (SVM) has been utilized for classifying students’ diverse levels of outcomes and anticipating students’ performances. The input dataset for both training and testing were taken by merging the values obtained from two surveys done on students and experts utilizing an adaptive neuro-fuzzy interference system (ANFIS). The application of the proposed model can moreover be enhanced in predicting course-wise performances of the students and its precision can too be improved by adding new factors, increasing survey participants