<![CDATA[The rapid advancement of data-driven technologies has transformed the landscape of educational innovation, particularly within learning factory environments that simulate real industrial settings for experiential learning. This study aims to evaluate the effectiveness of various machine learning techniques in monitoring student performance and facilitating continuous improvement in the learning process. Using a quantitative approach, data were collected from student activities, production logs, and performance metrics within a university-based learning factory over one academic term. Several machine learning algorithms, including Decision Tree, Random Forest, and Support Vector Machine, were applied to predict student performance levels and identify critical factors influencing learning efficiency. The analysis revealed that ensemble based models, especially Random Forest, achieved the highest prediction accuracy and provided valuable insights into performance trends, enabling proactive instructional interventions. Additionally, the integration of predictive analytics contributed to improved feedback mechanisms and optimization of task allocation, fostering both individual and group learning outcomes. The findings highlight the significant potential of machine learning in enhancing performance monitoring systems and promoting data informed decision-making in educational manufacturing contexts. This study concludes that the strategic adoption of machine learning techniques can substantially strengthen the feedback loop between learners and instructors, leading to more adaptive, efficient, and sustainable learning processes within the learning factory framework.]]>
Copyrights © 2025
