AI-Driven Robo-Advisory Integration in Banking: A Machine Learning and Behavioral Analysis of Retail Investor Adoption

Abstract

This study examines the adoption of bank-integrated robo-advisory services among retail investors in the context of increasing AI integration in banking. Using data from 182 respondents, the study analyzes the impact of perceived usefulness, ease of use, ethical transparency, operational efficiency, customer experience, perceived value, and customer trust on adoption intention. A combination of statistical and machine learning techniques including correlation, regression, decision trees, random forests, and cluster analysis was employed. The findings suggest that perceived value and customer trust are the strongest predictors of adoption intention. The results highlight that successful implementation of robo- advisory services depends not only on technological efficiency but also on psychological and value-based factors.