<![CDATA[This study investigates the utilization of English score data as an indicator of graduate learning outcomes achievement in Informatics Engineering programs through a data-driven approach. A dataset comprising 9894 student English Score records was analyzed using a combination of descriptive statistics, machine learning classification, clustering techniques, and deep learning models. The study aims to evaluate students’ English proficiency levels and explore the potential of artificial intelligence (AI) methods in supporting academic decision-making. The results reveal that the average English score (235.78) is significantly below the CPL threshold (≥260), with only 33.90% of students meeting the required standard, indicating a substantial gap in English proficiency achievement. Classification models demonstrate strong predictive capability in distinguishing student performance categories, while clustering analysis reveals distinct groupings of student proficiency levels. Furthermore, a 1D Convolutional Neural Network (CNN) model demonstrates the feasibility of deep learning approaches in modeling educational data. The findings highlight the importance of integrating AI-based analytics into academic evaluation systems to support Outcome-Based Education (OBE). This study contributes to the development of a data-driven framework for continuous quality improvement and provides insights for designing targeted interventions to enhance student competencies..]]>
Copyrights © 2026
