Mapping Research Trends and Future Research Directions in Robo-advisory: A Structural Topic Modelling Approach

Abstract

Robo-advisory services have revolutionized the investment landscape by leveraging advanced technology to provide automated and personalized investment guidance to investors. We explore key research themes addressed in the literature on robo-advisory and identify research avenues that can further advance understanding of this field. We analyzed 555 articles and used latent Dirichlet allocation, a text-mining approach to structural topic modelling, using Python. This resulted in 15 topics, which were further classified into different clusters and themes to identify the potential research areas. Our research provides sustainable insights and solutions that support researchers, robo-advisors and regulators in maximizing the benefits of robo-advisory services.