The Role of Machine Learning in Supporting Entrepreneurial Decision-Making

Abstract

This study investigates the role of machine learning (ML) in supporting entrepreneurial decision-making by employing a mixed-methods design that combines quantitative experimentation with qualitative interviews. Using financial, market, and entrepreneurial datasets, ML models including Random Forest, Gradient Boosting, and Artificial Neural Networks were trained and evaluated for their ability to predict venture survival, assess financial risk, and identify opportunities. Results demonstrate that ensemble- based ML models consistently outperform traditional methods in terms of accuracy, recall, and F1- scores, while explainable AI tools such as SHAP enhance transparency and trust in predictions. Twelve figures and nine tables illustrate how ML contributes to accuracy improvements, error reduction, and interpretability, while qualitative findings highlight both enthusiasm for predictive insights and concerns about algorithmic bias and ethical implications. The study emphasizes that ML effectiveness is context- dependent, with industry-specific variations in predictive performance. It further underscores the importance of data scale, showing that larger datasets improve recall and robustness. By integrating computational intelligence with entrepreneurial judgment, ML emerges as a transformative enabler of resilience, agility, and innovation in uncertain markets. The research contributes to the growing literature on digital entrepreneurship and offers actionable insights for entrepreneurs, policymakers, and investors seeking to leverage ML responsibly for sustainable business growth.