Crafting Portfolios Tailored to Investor Preferences with Generative AI

Abstract

Investors often face challenges aligning portfolios with specific preferences or regulatory constraints, such as avoiding commodities. Can machine learning offer a solution? Using Graphical Models, we frame this as an inference problem to replicate a desired fund within set constraints. Our approach achieves a high correlation with the target portfolio, allowing cost-effective replication. An example to decoding global macro hedge funds is provided. It shows very stable correlation emphasizing that the method is able to replicate the strategy even under some strong investment constraints.

Keywords: Graphical Models, portfolio replication, investor preferences

JEL Classification: G11, G17, G23