top of page
Published in
Visionary Voices
MINING HIGH SCHOOL TO UNIVERSITY ACADEMIC PERFORMANCE PATTERNS IN INFORMATION TECHNOLOGY EDUCATION USING DESCRIPTIVE AND ASSOCIATION RULE MODELS
Visionary Voices, 1(8), 8, ISSN: 3082-4389, 2025.
Recommended Citation:
Tano, I. M. (2025). MINING HIGH SCHOOL TO UNIVERSITY ACADEMIC PERFORMANCE PATTERNS IN INFORMATION TECHNOLOGY EDUCATION USING DESCRIPTIVE AND ASSOCIATION RULE MODELS. In Visionary Voices (Vol. 1, Number 8, p. 8). Lakbay-Diwa Publishing. https://doi.org/10.5281/zenodo.17973923
Author(s)
Tano, Isagani M.
Description
Educational Data Mining (EDM) has emerged as a critical research area for extracting actionable insights from academic databases to support institutional decision-making. While data mining techniques have been widely applied in business domains, their application in higher education—particularly for student admission and academic planning—remains underexplored. This study investigates academic performance patterns of students enrolled in Information Technology Education (ITE) programs by analyzing their major subject grades in relation to the high schools they attended. Using the CRISP-DM methodology, institutional academic records from 2009 to 2015 were preprocessed and analyzed through descriptive statistics, cross-tabulation analysis, and association rule mining. Apriori and Predictive Apriori algorithms were applied using WEKA to uncover frequent itemsets and hidden relationships among ITE subject performance and secondary school background. The results reveal consistent associations between performance in foundational ITE subjects—such as Database Systems, Systems Analysis and Design, and Software Engineering—and subsequent outcomes in Multimedia Development, with notable patterns linked to specific high schools. The findings demonstrate that descriptive and association rule models can effectively identify subject-area proficiencies and weaknesses attributable to students’ secondary education backgrounds. These insights provide empirical support for data-driven college admission strategies, curriculum planning, and targeted academic interventions in higher education institutions.
bottom of page