Application of Machine Learning to Personalization of Adaptive Curriculum in Indonesian Middle Schools

In recent years, there has been increasing interest in utilizing Machine Learning (ML) to personalize the learning experience in educational settings. The application of ML in middle school curriculums in Indonesia presents an opportunity to enhance adaptive learning models tailored to individual students’ needs. This study aims to explore the potential of integrating ML algorithms to create a personalized, adaptive curriculum for middle school students. The primary objective is to evaluate how ML can optimize learning outcomes by adjusting content delivery based on student performance and learning patterns. Using a mixed-methods approach, the research combines qualitative data from educators and quantitative data from student performance metrics to design a model for adaptive learning. The ML algorithms used include decision trees, clustering, and reinforcement learning, which adaptively modify the curriculum based on real-time student feedback. The results show a significant improvement in student engagement and academic performance, with tailored content leading to better learning outcomes. The study concludes that ML-driven personalization can be effectively integrated into middle school curriculums, offering a scalable solution to enhance educational quality in Indonesia.