Prognosis of entrepreneurial traits among agricultural undergraduate students in India using machine learning

Purpose - This study aimed to understand the agri-entrepreneurial traits of undergraduate university students using machine learning (ML) algorithms. Design/methodology/approach - This study used a conceptual framework of individual-level determinants of entrepreneurship and ML. The Google Survey instrument was prepared on a 5-point scale and administered to 656 students in different sections of the same class during regular virtual classrooms in 2021. The datasets were analyzed and compared using ML. Findings - Entrepreneurial traits existed among students before attending undergraduate entrepreneurship courses. Establishing strong partnerships (0.359), learning (0.347) and people-organizing ability (0.341) were promising correlated entrepreneurial traits. Female students exhibited fewer entrepreneurial traits than male students. The random forest model exhibited 60% accuracy in trait prediction against gradient boosting (58.4%), linear regression (56.8%), ridge (56.7%) and lasso regression (56.0%). Thus, the ML model appeared to be unsuitable to predict entrepreneurial traits. Quality data are important for accurate trait predictions. Research limitations/implications - Further studies can validate K-nearest neighbors (KNN) and support vector machine (SVM) models against random forest to support the statement that the ML model cannot be used for entrepreneurial trait prediction. Originality/value - This research is unique because ML models, such as random forest, gradient boosting and lasso regression, are used for entrepreneurial trait prediction by agricultural domain students.