DOAJ Open Access 2025

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 Samyak Sanat Jain

Abstrak

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.

Penulis (3)

R

R. L. Manogna

A

Ashray Kashyap

S

Samyak Sanat Jain

Format Sitasi

Manogna, R.L., Kashyap, A., Jain, S.S. (2025). Is there a universal fit? Employing machine learning to investigate the diversity and prominence of factors influencing early-stage entrepreneurship. https://doi.org/10.1186/s13731-025-00578-6

Akses Cepat

PDF tidak tersedia langsung

Cek di sumber asli →
Lihat di Sumber doi.org/10.1186/s13731-025-00578-6
Informasi Jurnal
Tahun Terbit
2025
Sumber Database
DOAJ
DOI
10.1186/s13731-025-00578-6
Akses
Open Access ✓