Predicting Entrepreneurial Resilience and Sustainable Growth Intentions Among Women Entrepreneurs Through Explainable Artificial Intelligence: An Xgboost-Shap Analytics Approach

Abstract

Women entrepreneurs play a crucial role in fostering economic development, innovation, and inclusive growth, however, sustaining long-term business growth remains a significant challenge due to technological, psychological, and environmental constraints. This study investigates the determinants of Sustainable Growth Intention (SGI) among women entrepreneurs by developing an integrated framework comprising Digital Entrepreneurial Capability (DEC), Entrepreneurial Psychological Capital (EPC), Innovation Agility (IA), Entrepreneurial Ecosystem Support (EES), and Business Adaptability Capability (BAC). Based on the Resource-Based View and Dynamic Capability Theory, the study examines the direct and indirect relationships among these constructs.
A quantitative research design was employed using survey data collected from women entrepreneurs operating across Southern Rajasthan, India. The proposed framework was evaluated through Structural Equation Modeling (SEM), while Explainable Artificial Intelligence (XAI) techniques, including Extreme Gradient Boosting (XGBoost) and SHapley Additive exPlanations (SHAP), were utilized to enhance predictive accuracy and model interpretability. The findings reveal that DEC (β = 0.238, p < 0.001), EPC (β = 0.281, p < 0.001), IA (β = 0.197, p < 0.001), and EES (β = 0.171, p < 0.001) significantly influence Business Adaptability Capability. Furthermore, BAC exerts a substantial positive effect on Sustainable Growth Intention (β = 0.634, p < 0.001) and significantly mediates all proposed relationships. The model explains 59.2% of the variance in BAC and 53.4% of the variance in SGI. From a predictive perspective, XGBoost outperformed conventional regression and SEM prediction models, achieving an R² of 0.748. SHAP analysis identified BAC as the most influential predictor of SGI, followed by EPC, DEC, IA, and EES.
Study contributes to entrepreneurship literature by integrating explanatory and predictive analytical approaches and offers practical insights for policymakers and entrepreneurship-support institutions seeking to strengthen the sustainable growth potential of women-owned enterprises.