This study introduces a machine learning approach to estimate emotional yields of collectibles. Using 110 years of data, it shows most collectibles earn positive emotional returns (~2.5% annually), which lower their equilibrium financial returns.
Interested in having your article published in the Financial Analysts Journal? Find out how.
Abstract
We propose a novel method to estimate emotional yields of collectibles based on factor-mimicking portfolios. Using up to 110 years of collectibles returns for 13 distinct asset classes, we apply machine learning techniques to address challenges from non-synchronous trading. We use these estimates to study how emotional yields affect equilibrium pricing. Emotional yield estimates for 24 of our 30 collectibles return series are positive, with an annualized mean (median) of 2.64% (2.53%). Despite various forms of underestimation, these results provide evidence that assets with positive emotional returns have lower equilibrium financial returns.