Leveraging Machine Learning to Examine Engineering Students Self-selection in Entrepreneurship Education Programs
Effective Years: 2024-2026
This project aims to serve the national interest by advancing the understanding of undergraduate engineering students' participation in entrepreneurship education programs. Entrepreneurship and innovation are important for economic success, and engineers often hold a central role in leading innovation in today's high-technology world. To compete successfully in the global technological innovation economy, graduating engineers need to possess entrepreneurial skills to identify opportunities and understand market and business needs. Entrepreneurship education programs continue to be recognized as a mechanism for developing entrepreneurial skills and innovativeness in engineering and other STEM graduates. With increasing evidence supporting the advantages of entrepreneurship programming, it is important to ensure that broader engineering student populations are exposed to entrepreneurship programming. However, students often self-select into entrepreneurship education programs, and there is a lack of research in this regard. The project examines engineering students' self-selection by investigating the research question: How do engineering students' demographic, socio-economic, and academic backgrounds predict their participation in engineering entrepreneurship programs? By building a research-based understanding of student participation in entrepreneurship education programs, this individual investigator development project serves the national interest by providing insights for outreach, recruitment, and programmatic efforts, to widen the impact of these programs in undergraduate engineering education. The project uses innovative quantitative methods to examine how engineering students' demographic and academic background interactively predict their enrollment (or non-enrollment) in entrepreneurship education programs.
As the STEM education community continues to develop innovative educational interventions, it is critical to investigate which students are enrolling in such programs, particularly from a demographic standpoint. Drawing on social selection theory that highlights the importance of students' backgrounds, the goal of this project is to leverage regression and machine learning techniques as an exploratory, data-driven approach to examine engineering students' engagement in entrepreneurship education programs. Because background factors are likely to be associated with each other in complex ways, the focus of the project is to examine social selection using an interactionist view which examines the dynamic interplay of student demographic factors. The project contributes to advancing conceptual understanding by providing data-driven models explaining student participation that lay the foundation for future research in the emerging field of engineering entrepreneurship education. In addition, the project will study the effectiveness and suitability of regression-based methods and advanced machine learning modeling techniques (and their algorithmic variants), which can advance the use of similar approaches in engineering education research. This project is supported through a partnership with the Bill & Melinda Gates Foundation, Schmidt Futures, and the Walton Family Foundation. This project is also supported by NSF's EDU Core Research Building Capacity in STEM Education Research (ECR: BCSER) program, which is designed to build investigators' capacity to carry out high-quality STEM education research in the core areas of STEM learning and learning environments, broadening participation in STEM fields, and STEM workforce development.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.