In the era of burgeoning AI technology and progressive educational systems, AI’s influence on education has become increasingly apparent. The intricacies between courses continue to intensify, heightening the need for researchers to conduct precise correlation analyses. Traditional practices, which rely solely on correlation coefficients, tend to focus on linear relationships between two courses, leaving much to be desired. To delve deeper into the relationships between multiple courses, a growing number of AI-assisted methodologies have emerged in the education arena. Consequently, we introduce the Multilayer Perceptron (MLP) course relation approach, which scrutinizes the direct relationships embedded within grade data. Empirical evidence highlights the proposed MLP course correlation method’s capacity to reveal nonlinear and profound associations across multiple courses, showcasing its potential to revolutionize course correlation analysis.