Technology acceptance prediction of robo-advisors by machine learning

Whether a new technology can spread smoothly in the market heavily depends on the user's acceptance of the technology. A considerable number of studies have sought to predict user acceptance intention through numerous methods. Most rely on the researcher's design and thus cannot present an optimized model that truly meets the research question. This study aims to provide a machine learning approach to predict the user's technology acceptance intention within the framework of robo-advisors. The new approach implements a predictive model from multiple machine learning algorithms such as regression tree, random forest, gradient boosting, and artificial neural network, and then compares the model with the traditional regression analysis methodology. All machine learning algorithms showed superior prediction performance than linear regression. Specifically, gradient boosting showed the best performance and perceived pleasure showed the greatest importance. This research ultimately provides theoretical implication regarding the perspective of acceptance prediction methodology and practical implication about which factors are crucial to acceptance of robo-advisors.