Learning risk preferences from investment portfolios using inverse optimization

The level of risk an investor can endure, known as risk-preference, is a subjective choice that tightly related to psychology and behavioral science in decision making. This paper presents novel approach measuring preference from existing portfolios using inverse optimization on mean–variance portfolio allocation framework. Our allows the learner continuously estimate real-time preferences concurrent observed market price data. We demonstrate our methods robotic investment real data consists 20 years asset pricing 10 mutual fund holdings. Moreover, quantified parameters are validated with two well-known measurements currently applied field. proposed could lead practical fruitful innovations automated/personalized management, such Robo-advising, augment financial advisors’ intelligence long-term horizon.