Personalized Robo-Advising: Enhancing Investment Through Client Interaction

Automated investment managers, or robo-advisors, have emerged as an alternative to traditional financial advisors. The viability of robo-advisors crucially depends on their ability offer personalized advice. We introduce a novel framework in which robo-advisor interacts with client solve adaptive mean-variance portfolio optimization problem. risk-return tradeoff adapts the client’s risk profile, idiosyncratic characteristics, market returns, and economic conditions. show that optimal strategy includes both myopic intertemporal hedging terms reflect dynamic profile client. characterize personalization via faced by between receiving information from timely manner mitigating behavioral biases communicated profile. argue portfolio’s Sharpe ratio return distribution improve if counters tendency reduce exposure during contractions when is more favorable. This paper was accepted David Simchi-Levi, stochastic models simulation.