One Size Fits All? Using Machine Learning to Study Heterogeneity and Dominance in the Determinants of Early Stage Entrepreneurship

Despite the importance of entrepreneurship to economic and social development, few studies have focused on the relative importance of the determinants of entrepreneurship. Moreover, traditional regression based approaches are unable to fully capture heterogeneous and complex non-linear patterns in the determinants of entrepreneurship. To address these limitations, we adopt a machine learning approach to study heterogeneity and dominance in the determinants of early stage entrepreneurship. We focus on the application of decision tree algorithms to a large scale dataset from the Global Entrepreneurship Monitor. Our results reveal that the dominant determinants are individual entrepreneurial self-efficacy and networks, with factors such as cultural perceptions being relatively unimportant, despite their attention in the wider literature. The results also show that different combinations of factors can lead to entrepreneurship, highlighting the heterogeneity of entrepreneurs