Integration of higher education student management and pedagogical concepts based on data-based decision making

Abstract

In the context of big data’s growing influence on education, our study presents a novel approach to managing higher vocational student data through a model based on the “three-round education” philosophy. We construct a predictive model to dissect and categorize student performance at X higher vocational college by integrating K-prototypes and LSSVM algorithms. Our findings reveal three primary groups: high achievers (43.65%), average performers (23.38%), and those with challenges (32.97%), each showing apparent differences in academic success indicators. Impressively, the model forecasts student enrollment numbers with less than 1.077% error, providing a reliable tool for educational administrators to make informed decisions and tailor student management strategies effectively.

Keywords

• k-prototypes algorithm
• ls-svm
• student clustering
• data prediction
• student management decisions
• 00a35