Is there a universal fit? Employing machine learning to investigate the diversity and prominence of factors influencing early-stage entrepreneurship

R. L. Manogna (), Ashray Kashyap () and Samyak Sanat Jain ()
Additional contact information
R. L. Manogna: Birla Institute of Technology and Science, Pilani, K K Birla Goa Campus
Ashray Kashyap: Birla Institute of Technology and Science, Pilani, K K Birla Goa Campus
Samyak Sanat Jain: Birla Institute of Technology and Science, Pilani, K K Birla Goa Campus

Journal of Innovation and Entrepreneurship, 2025, vol. 14, issue 1, 1-26

Abstract: Abstract In recent years, understanding the determinants of Entrepreneurial Intentions (EI) among young individuals has gained significant attention worldwide. This study attempts to empirically investigate this phenomenon across 50 economies using the 2024 Global Entrepreneurship Monitor (GEM) dataset of working-age individuals (18–35 years), employing machine learning techniques to uncover influential factors of entrepreneurial intention. We apply machine-learning models such as Decision Trees, Random Forests, and XGBoost (Extreme Gradient Boosting) algorithms to our predictive model. Among these methods, Random Forest exhibited the highest predictive accuracy. We use 12 variables encompassing cognitive and behavioral factors, economic status, and neighborhood influence as predictors of Entrepreneurial Intentions. By running the model separately for low, middle, and high-income economies we draw a contrast between the differences in the factors affecting Entrepreneurial Intentions in each. The analysis reveals that networks, skills, and creativity play pivotal roles in shaping entrepreneurial intentions, with education emerging as a crucial determinant, particularly in lower-income countries. Creativity also emerges as a vital driver, especially in middle and high-income countries, emphasizing innovative thinking’s role. Furthermore, household situations, such as larger family sizes, exhibit positive correlations with higher entrepreneurial intentions. Neighborhood support is significant in low-income countries, highlighting socio-cultural influences. Continued research is needed to deepen our understanding of entrepreneurial motivations and barriers. Future studies could include longitudinal research to track intentions over time and comparative analyses across cultures. Qualitative methods can complement quantitative analyses by providing insights into the drivers of entrepreneurial aspirations.

Keywords: Entrepreneurial intentions; Global entrepreneurship monitor; Early-stage entrepreneurial activities; Random forest; Machine learning; Artificial intelligence (search for similar items in EconPapers)
JEL-codes: L26 L31 M13 O30 O57 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1186/s13731-025-00578-6 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:joiaen:v:14:y:2025:i:1:d:10.1186_s13731-025-00578-6

Ordering information: This journal article can be ordered from
https://innovation-e ... ip.springeropen.com/

DOI: 10.1186/s13731-025-00578-6

Access Statistics for this article

Journal of Innovation and Entrepreneurship is currently edited by Elias G. Carayannis

More articles in Journal of Innovation and Entrepreneurship from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().