<![CDATA[This study aims to provide a comprehensive overview of the application of Bayesian probability in supporting students' academic decision-making, encompassing graduation prediction, major selection, learning performance mapping, and the design of adaptive instructional interventions. This research employs a literature review method by examining national and international scientific publications from the last decade to obtain an in-depth understanding of the effectiveness of Bayesian approaches. In this study, Bayes' theorem functions as an analytical mechanism for updating prior information with new evidence, resulting in more accurate posterior estimations that realistically reflect students’ academic conditions. The findings indicate that the Bayesian approach not only enhances the accuracy of academic outcome predictions but also minimizes bias in student assessment and strengthens the quality of individualized learning interventions. The integration of Bayesian probability with AI-based digital learning systems further supports the provision of personalized learning recommendations, real-time performance monitoring, and data-responsive academic decision-making. This study concludes that Bayesian probability holds significant potential as a foundation for developing modern academic decision-support systems that are more objective, adaptive, and aligned with students’ individual learning needs]]>
Copyrights © 2025
