MODELLING ENTREPRENEURIAL INCLINATION WITH AN ARTIFICIAL NEURAL NETWORK

ABSTRACT Artificial neural networks are parallel processing systems with the ability to learn by example and to generalize from inferred patterns. In this application, a neural network model of the feedforward, backpropagation type was designed to predict entrepreneurial inclination from knowledge of psychological, demographic and family characteristics. Training and testing data were drawn from results of a previous study, in which a questionnaire was administered to 200 business undergraduates in Hong Kong. The trained network had a holdout test accuracy of 80%. The results suggest a potential usefulness of neural network technology for non-mechanistic modeling in entrepreneurship research and application.