PERSONALIZED LEARNING USING MACHINE LEARNING

Use of traditional methods of learning, which often cannot engage every learner effectively, does challenge the diversity of student learning preferences. This paper addresses this problem by developing a Learning Style Model using machine learning techniques in predicting individual learning preference . The study analyzes the available Learning Style Models and tests various Machine Learning models based on filtered datasets with specific data-gathering tools. The defining factor is to determine the significant factors that affect the learning style. Preliminary results reveal that an optimized model of Machine Learning does improve the precision in identifying the choice of learning preferences. The results of this study are therefore of wide applicability in using personalized learning plans, adaptive instruction, early student support, and data-driven educational strategies. It advances personalized education into a predictive model that supports overall educational needs outside a one-size-fits-all mold.

This project demonstrates the potential of using machine learning to enhance personalized learning through the VARK model. By analyzing existing datasets, we identified effective algorithms for predicting learning styles. Our approach provides a framework that can adapt to individual preferences, improving educational outcomes and engagement. As we will be expanding our data collection through targeted questionnaires among college students, we anticipate refining our model for even greater accuracy and effectiveness. This effort paves the way for adaptive learning systems that cater to diverse learning needs, fostering a more efficient and customized educational experience that evolves with student data over time.