Robo-Advisors Estimate Clients' Risk Aversion Using Adaptive Questionnaires
A research paper proposes a framework for robo-advisors to estimate non-expert clients' risk aversion using adaptive binary-choice questionnaires, modeling risk aversion with cost functions and spectral risk measures in a static setting. The authors prove finite-sample identifiability and establish a sqrt(N) convergence rate up to logarithmic factors, introduce a distinguishing-power criterion that enables efficient question design achieving accurate learning with fewer than 50 questions in simulations, and present preliminary qualitative identifiability results for a discounted infinite-horizon extension.
Key Points
- 1Proves finite-sample identifiability and sqrt(N) convergence rate for static risk-aversion estimation.
- 2Introduces distinguishing power metric to optimize questionnaire design, improving estimation efficiency.
- 3Achieves accurate learning in simulations with fewer than 50 adaptive binary questions.
Scoring Rationale
Provides provable identifiability and practical question design, but remains a single academic source with limited real-world validation.
Sources
Public references used for this report.
Practice with real Ad Tech data
90 SQL & Python problems · 15 industry datasets
250 free problems · No credit card
See all Ad Tech problems
