Fund2Persona: A Framework for Building and Refining Financial Advisor Personas from Fund Disclosure Data
Teaching AI financial advisors to think like real fund managers, not generic chatbots
Researchers built Fund2Persona, a system that creates AI financial-advisor personas by studying actual fund holdings, manager decisions, and market commentary rather than relying on generic prompts. The resulting personas gave more specific and useful investment advice, better predicted what portfolio moves a manager would make, and generated more varied investment perspectives than standard AI advisors.
Financial advisory is expensive and scarce—most people can't afford personalized guidance. This framework could make expert portfolio-management logic scalable and available through AI systems that actually understand *how* a specific manager thinks, not just what generic best practices are. The difference matters: an AI trained on a growth-stock specialist's real decisions will steer a portfolio differently than one trained on boilerplate advice, and clients get recommendations tailored to actual investment philosophies rather than one-size-fits-all rules.