Predicting Student Performance in a Design Entrepreneurship and Leadership Course: Leveraging Academic Metrics

Abstract

Predicting and understanding student performance is a critical challenge for design education programs, as it enables educators to identify at-risk students, allocate resources effectively, and enhance teaching strategies to support student success. This study investigates the use of academic metrics to develop a predictive model for student performance in a "Design Entrepreneurship and Leadership" course at Effat University. The academic record data collected includes student attendance, quiz grades, midterm exam grades, final exam grades, and assignment project grades. Using a multiple linear regression approach, this research examined the relative influence of these factors on the students' final course performance. The results indicate that quiz grades, midterm exam grades, and assignment project grades were the strongest predictors of student success, while attendance grades also contributed significantly to the model. The proposed predictive model provides valuable insights for design educators and program administrators. By understanding the key drivers of student performance, they can identify at-risk students early on and implement targeted interventions to improve learning outcomes. Additionally, the findings can inform curriculum development, assessment practices, and the allocation of resources within design program’s other courses. This study contributes to the limited but growing body of research on predicting student performance in design-focused courses. By leveraging academic metrics, the researchers demonstrate a rigorous and data-driven approach to forecasting student success, which can be adapted and applied to a variety of design education contexts. The findings have important implications for enhancing the quality and effectiveness of design curricula, ultimately preparing students for the complex challenges they will face in the professional world.