Neural network in the learning material recommendation system based on individual learning styles

Technological developments in education have encouraged innovations in learning systems that are more adaptive and personalized. One of the approaches that is growing rapidly is the Neural Network-based learning material recommendation system, which can adapt the material to individual learning styles. Each student has a unique learning style, such as visual, auditory, and kinesthetic, which affects the effectiveness of their understanding of the material. This study aims to analyze how the Neural Network-based recommendation system can optimize the learning experience of students by adjusting learning materials based on individual learning styles. Specifically, this study explores how the Neural Network model identifies students' learning styles, evaluates the effectiveness of the recommendations provided by the system, and examines the challenges and opportunities in its application in educational settings. This study uses a qualitative approach with the literature review method. Data were collected from various scientific journals, books, and conference proceedings discussing the implementation of Neural Networks in the learning recommendation system. The analysis shows that the Neural Network-based system can improve student engagement and understanding through material recommendations that are more suitable for individual learning styles. However, challenges such as student data protection, bias in recommendations, and integration with formal curricula are still major obstacles. With the development of increasingly advanced technology, this system has great potential to be adapted more widely in the world of education.