Educational Data Mining to Predict Bachelors Students’ Success

Predicting academic success is essential in higher education because it perceived as a critical driver for scientific and technological advancement countries’ economic social development. This paper aims to retrieve the most relevant attributes by applying educational data mining (EDM) techniques Portuguese business school bachelor’s historical data. We propose two predictive models classify each student regarding at enrolment end of first year. implemented SEMMA methodology tried several machine learning algorithms, including decision trees, KNN, neural networks, SVM. The best classifier entry-level reached random forest with an accuracy 69%. At year, MLP artificial network’s performance was achieved 85%. main findings show that or grades and, thus, student’s previous engagement environment are decisive achieving success. Doi: 10.28991/ESJ-2023-SIED2-013 Full Text: PDF