“Enhancing Student Engagement in New Business Discipline Experimental Teaching Through Smart Resource Allocation Systems”

This paper designs and validates an intelligent resource allocation system aimed at optimizing resource distribution in business experimentation teaching through the use of machine learning algorithms (Random Forest). The system dynamically adjusts teaching resources based on the analysis of student behavior data, including task completion time, test scores, and engagement, to provide personalized learning support. The experiment involved 52 students divided into high-performance, moderate-performance, and low-performance groups, with student behavior data collected through the Superstar Learning platform. The results demonstrate that the intelligent resource allocation system significantly improved student engagement and learning outcomes, particularly for low-performance students, who showed substantial improvement in both engagement and test scores. Additionally, the system's performance evaluation revealed high resource allocation efficiency and rapid feedback response times across different scenarios. The paper also discusses the advantages and limitations of the system, confirming its potential application in real-world teaching.