2026-10-09T03:40:16Z https://api.figshare.com/v2/oai

oai:figshare.com:article/32805230 2026-10-01T16:17:18Z portal_1172 item_type_8 month_year_10_2026

The social cognitive and institutional determinants of entrepreneurial intentions: a machine learning approach Liang Xu (102656) PUREID: 669008112 Machine Learning social cognitive theory institutional theory Global Entrepreneurship Monitor SHapley Additive exPlanations entrepreneurship Entrepreneurial intention configurational approach sankey graph chord graph Systematic Literature Review This thesis advances the field of entrepreneurship research by leveraging machine learning (ML) algorithms to explore heterogeneity and dynamics in the determinants of entrepreneurial intentions (EIs). The research begins with a systematic literature review of studies employing machine learning algorithms in entrepreneurship research. Using ML techniques, the reviewed papers are visualised and systematically profiled, providing a comprehensive mapping of the research landscape. The first study draws on Global Entrepreneurship Monitor (GEM) dataset, underpinned by Social Cognitive Theory (SCT), to investigate heterogeneity in the determinants of EIs. A configurational approach, using a machine learning algorithm complemented by explainable artificial intelligence technique, is employed to uncover key predictors and their interactions. The second study employs various machine learning algorithms to examine the dynamic nature of entrepreneurial factors contributing to EIs over time, particularly before, during, and after the 2008 financial crisis.The third study shifts focus to the country-level EIs, drawing on Institutional Theory and longitudinal global GEM data, as well as contextual data, to explore how institutional and contextual factors shape country-level EIs. Thesis is embargoed until 31 July 2030. 2026-10-01T16:17:18Z Text Thesis 10.17034/32805230.v1 https://figshare.com/articles/thesis/The_social_cognitive_and_institutional_determinants_of_entrepreneurial_intentions_a_machine_learning_approach/32805230 All Rights Reserved Open Access after 2030-07-31