Philippine Standard time

Bridging the Gap: A Comparative Analysis of Traditional and Neural Network Regression Methods for Predicting University Entrant Performance in SUAST Examination

In developing countries like the Philippines, access to free and high-quality tertiary education is crucial for better job opportunities. The State University Aptitude and Scholarship Test (SUAST) is used as a college admission examination by Davao Oriental State University (DOrSU). However, the passing rate for SUAST was only 54% for the academic year 2018-2023, and non-passers were still accepted due to policy changes, which undermine the purpose of the examination. This study aimed to identify the factors that influence the performance of university entrants in the SUAST examination using a researcher-made survey questionnaire administered online, utilizing both multiple-layer perceptron neural network (MLPNN) and multiple linear regression analysis (MLR) methods. A sample size of 359 was recommended, and the study found that family income, senior high school general weighted average (SHSGWA), library entry, intrinsic goal, openness and intellect, and behavioral reaction were significant predictors of SUAST exam scores. MLPNN analysis further identified library access and resources, family income, and academic self-belief as the most important predictors of SUAST exam scores, and MLPNN outperformed MLR. This study provides recommendations for DepEd and HEI’s to enhance the preparation and performance of students taking the SUAST exam, such as offering study materials and test-taking strategies, evaluating alternative admission tests, and reviewing the content validity of the questionnaire. The study also suggests looking at other indicators of student readiness for university, such as high school grades and extracurricular activities, and conducting future research on the impact of financial aid and scholarships on academic achievement and performance disparities between male and female students.


This publication has been cited time(s).