DATA ENGINEERING AND VISUALIZATION OF STUDENT ACADEMIC PERFORMANCE USING BUSINESS INTELLIGENCE TOOLS

Abstract

The rapid growth of data in higher education institutions has created challenges in managing, analyzing, and interpreting student academic performance information. Academic data such as course grades, attendance, and assessment results are often scattered across multiple sources, making it difficult for decision-makers to gain comprehensive insights. This study presents the development of a data engineering and visualization framework designed to process and present student academic performance using business intelligence (BI) tools. The methodology involves several stages: data acquisition from academic information systems, data cleaning and transformation through a structured pipeline, and integration into a centralized database. Visualization was carried out using BI tools to generate interactive dashboards that provide multi-dimensional analysis of student achievement. The results demonstrate that the developed framework successfully consolidated student performance data into a single repository, enabling efficient analysis and visualization. Key performance indicators such as GPA trends, course completion rates, and subject-specific weaknesses were visualized in real time. These visualizations support lecturers, academic administrators, and students in identifying performance patterns, predicting potential risks, and formulating appropriate interventions. The novelty of this research lies in the combination of data engineering processes with user-friendly BI dashboards tailored for the education sector in Indonesia. In conclusion, the proposed system enhances transparency, accessibility, and decision-making in academic performance monitoring. It highlights the importance of integrating data engineering and visualization techniques in higher education, providing a foundation for more advanced analytics such as predictive modeling and personalized learning recommendations.