Innovation Performance Prediction of University Student Teams Based on Bayesian Networks

Many studies have been conducted on the impact of dualistic learning, knowledge sharing, member heterogeneity, and their influencing factors on team performance in enterprises. However, research on the substantial differences between university student teams and enterprise teams is scarce. To address this void, this empirical study explores how the mechanism of dualistic learning affects university student teams’ learning performance facing rapid changes in higher education. Using the questionnaire, two modules of dualistic learning were identified through reliability and validity tests, and the research data set was formed. After preprocessing the data set, two team innovation performance prediction models were established based on the Bayesian network (BN). According to the characteristics of BN, the probability reasoning of the model was calculated and the posterior probability table was obtained under different dualistic learning levels. The results show that dualistic learning has significant impacts on innovation performance, and the improvement of dualistic learning can stimulate team innovation performance. This research can provide important theoretical guidance for teams to improve their ability, gain competitive advantages, and stimulate the creative enthusiasm of college students. Hopefully, this research will enrich the existing theoretical connotation to a certain extent and promote the development of relevant empirical research.