Knowledge and fostering technology adoption intention for entrepreneurship education in Chinese higher education: A machine learning and fsQCA analysis

In the context of artificial intelligence (AI) reshaping the global entrepreneurial ecosystem, fostering students' technology adoption intention in entrepreneurship has become a critical issue in higher education. Traditional technology acceptance models are limited in their theoretical applicability and research methodologies. Therefore, this study adopts a two-stage prediction-configuration analysis framework, integrating machine learning and fuzzy-set qualitative comparative analysis (fsQCA) to identify key predictors and configurational pathways of technology adoption intention in entrepreneurship. This research is based on a sample of 4,665 university students in China. First, XGBoost-SHAP identified entrepreneurship courses, digital entrepreneurship self-efficacy, and entrepreneurship faculty as three core predictive variables. Second, fsQCA revealed three differentiated but equivalent paths to high technology adoption intention in entrepreneurship. Theoretically, integrating predictive analytics and configurational perspectives effectively overcomes the limitations of linear assumptions and net effect analysis. Moreover, a micro-meso-macro multilevel analysis framework extends the technology acceptance model (TAM) into a tripartite symbiotic system of learner-technology-educational ecosystem, thereby enhancing the model's contextual explanatory power. The findings discuss both the generalizability of technology adoption and the specificity of the Chinese higher education context. Practically, the results provide actionable recommendations for educators and policymakers. For instance, this framework supports the design of entrepreneurship courses tailored to students' entrepreneurial self-efficacy or prior experience. Such initiatives are crucial for stimulating students' innovative potential and fostering their technology adoption intention in entrepreneurship.