Modeling Economic Choice under Radical Uncertainty: Machine Learning Approaches

This paper utilizes a novel data on consumer choice under uncertainty, obtained in a laboratory experiment in order to gain substantive knowledge of individual decision-making and to test the best modeling strategy. We compare the performance of logistic regression, discriminant analysis, naïve Bayes classifier, neural network, decision tree, and Random Forest (RF) to discover that the RF model robustly registers the highest classification accuracy. This model also reveals that apart from demographic and situational factors, consumer choice is highly dependent on social network effects