A machine learning approach to rural entrepreneurship
Summary. Machine learning models trained on Life in Transition Survey data identify key factors associated with rural business success and failure across Eastern Europe and Central Asia. Capital constraints, age, trust levels, awareness of trends, media use, competitive character, institutional support, and education all predict entrepreneurial outcomes with 72–92% accuracy. The findings reveal which personal and structural factors determine whether rural entrepreneurs successfully launch businesses.
Cite this article
Celbiş, M. G.. (2021). A machine learning approach to rural entrepreneurship. Papers of the Regional Science Association. https://doi.org/10.1111/pirs.12595
Celbiş, Mehmet Güney. “A machine learning approach to rural entrepreneurship.” Papers of the Regional Science Association, 2021. https://doi.org/10.1111/pirs.12595.
Celbiş, Mehmet Güney. 2021. “A machine learning approach to rural entrepreneurship.” Papers of the Regional Science Association. https://doi.org/10.1111/pirs.12595.
@article{celbi-2021-machine-learning-approach-rural-entrepreneurship,
title = {A machine learning approach to rural entrepreneurship},
author = {Mehmet Güney Celbiş},
journal = {Papers of the Regional Science Association},
year = {2021},
doi = {10.1111/pirs.12595},
url = {https://doi.org/10.1111/pirs.12595}
}
TY - JOUR TI - A machine learning approach to rural entrepreneurship AU - Mehmet Güney Celbiş JO - Papers of the Regional Science Association PY - 2021 DO - 10.1111/pirs.12595 UR - https://doi.org/10.1111/pirs.12595 ER -
Details
- DOI
- 10.1111/pirs.12595
- Countries
- Netherlands
- Regions
- Europe
- Categories
- entrepreneurship, innovation-theory, rural-data-and-definitions
- Added
- 2026-04-28