Machine Learning based Analysis of the Effect of Team Competition on College Students’ Academic Performance

Abstract

Abstract In the field of Mobile Edge Computing (MEC), machine learning techniques present a promising avenue for intelligent integration and processing of data from MEC terminals. Our study delves into the intersection of Machine Learning with MEC terminal data, exploring the complexity of team competition mechanisms based on social identity and competition theory. This exploration aims to enhance student participation and enthusiasm within university classrooms. However, despite of its potential benefit, there are still many unresolved issues: What type of students and teams benefit more from team competition? In what teaching context is team competition more effective? Which competition design methods better increase student academic performance? To answer these questions, we first de-sign a randomized field experiment among freshmen enrolled in college English course. Then, we collected data using mobile devices and analyzed the observational data to predict the individual treatment effect of academic performance in college English through linear and nonlinear machine learning models. Finally, by carefully investigating features of teams and individual student, we reduce the prediction error by up to 30%. In addition, through interpreting the predictive models, we discover some valuable insights regarding the practice of team competition in college classrooms.