Machine Learning in Guided Reading Program Levelling

This study addresses the challenge of optimizing a guided reading program through the integration of machine learning models, with a specific focus on levelling students up. Investigating the use of machine learning models for this purpose, the research identifies random forest as the most effective model for precision and personalization in assessments. The analysis of SHAP values emphasizes the crucial role of reading accuracy and comprehension in achieving this optimization. Despite limitations in duration and dataset size, the findings significantly contribute to understanding the potential of machine learning in educational settings. Future research endeavors seek to overcome these limitations, diversify datasets, and explore findings’ adaptability for ESL learners. The study concludes with a commitment to ongoing efforts in autonomously exploring the guided reading application's effectiveness, user-friendliness, and the role of machine learning in shaping personalized learning experiences.