Application and optimization of digital situated teaching in university finance courses from a constructivist perspective: An analysis based on machine learning algorithms

The rapid advancement of digital technologies is prompting a necessary shift in traditional educational models, particularly in finance education. This study introduces the "Multi-Dimensional Situated Learning Model" (MD-SLM), which is rooted in constructivist theory and aims to enhance teaching strategies in university finance courses. The MD-SLM incorporates digital tools like simulation software and online learning platforms to create a dynamic and authentic learning environment that fosters active student engagement and the development of practical skills. The model is designed with a tiered structure of situational tasks-categorized as foundational, extended, and integrative-paired with a comprehensive teacher support system that helps educators transition from traditional teaching roles to facilitators of learning. To assess the model's effectiveness, machine learning algorithms, such as cluster analysis, decision tree analysis, and Gradient Boosting Machine (GBM), were used on a dataset of 514 students over three years. The results demonstrated significant improvements in student learning behaviors and outcomes. The study's findings highlight the MD-SLM's potential to revolutionize digital finance education by aligning with constructivist principles and providing customized learning experiences. The research concludes with recommendations for applying this model more broadly across various educational contexts, aiming to contribute to the ongoing digital transformation in higher education.