Towards designing robo-advisors for unexperienced investors with experience sampling of time-series data

Abstract

We propose an experimental study to examine how to optimally design a robo-advisor for the purposes of financial risk taking. Specifically, we focus on robo-advisors which are able to (i) “speak” the language of the investors by communicating information on the statistical properties of risky assets in an intuitive way, (ii) “listen” to the investor by monitoring her emotional reactions and (iii) do both. The objectives of our study are twofold. First, we aim to understand how robo-advisors affect financial risk taking and the revisiting of investment decisions. Second, we aim to identify who is most affected by robo-advice.