Wang Hongyuan, Ma. Visitacion Gumabay
ABSTRACT
This study aimed to design, develop, and implement a Students’ Performance Evaluation System with Data Analytics (DAS-CEEO) for Guangdong University of Science and Technology to address limitations in traditional student assessment, including fragmented data, subjective evaluations, and insufficient tracking across the five education domains: Morality, Intellectual, Physical, Aesthetic, and Labor. The study employed a descriptive-developmental research design and utilized the Agile Scrum methodology for system development. The system integrates multi-source student data, applies data mining techniques such as clustering, classification, and association rules, and incorporates machine learning algorithms for predictive analytics. Evaluation was conducted by ten IT experts using the ISO/IEC 25010 software quality standard, resulting in an overall mean score of 4.51 (Very Great Extent), with particularly high ratings in functional suitability, security, and compatibility. The DAS-CEEO provides a unified platform for real-time performance tracking, automated scoring, multi-level review, and visualized reporting, enhancing the objectivity and efficiency of student assessment while supporting the transition from score-centric evaluation to capability-oriented education.
Keywords: Data analytics, data mining, educational assessment systems, predictive analytics, student performance evaluation
https://doi.org/10.57180/bprl4068