In the dominant approach, it is assumed that risk preferences reflect the shape of utility function. Here, the alternative approach is, in which risk preferences are result of: (1) individual differences in focus on either potential or security that impacts decision weights put to good and bad...

We introduce a reinforcement learning framework for retail robo-advising. The robo-advisor does not know the investor's risk preference, but learns it over time by observing her portfolio choices in different market environments. We develop an exploration-exploitation algorithm which trades off...