Fund2Persona: A Framework for Building and Refining Financial Advisor Personas from Fund Disclosure Data
2026-06-29 • Computation and Language
Computation and Language
AI summaryⓘ
The authors created Fund2Persona, a system that builds financial advisor personas based on real fund data like disclosures and market info, instead of just using simple role prompts. Their method helps AI better mimic how actual fund managers think and make decisions. When tested, these personas gave more accurate and personalized investment advice compared to generic AI advisors. They also showed improved ability to imagine different market scenarios and offer advice tailored to individual investors. Overall, the authors demonstrate a way to make AI financial advisors more expert and specific by grounding them in real fund data.
financial advisor personalarge language model (LLM)fund disclosuresholdings transitionsmarket contextmanager commentaryagentic loopportfolio decisionsinvestment advicescenario generation
Authors
Suhwan Park, Hoyoung Lee, Zhangyang Wang, Alejandro Lopez-Lira, Young Cha, Chanyeol Choi, Jaewon Choi, Yongjae Lee
Abstract
Demand for personalized financial advising is growing, but consistent advisor expertise is difficult to obtain, scale, and encode in LLM systems. Simple persona prompts rarely specify how a financial advisor should reason and often drift toward generic recommendations. We propose Fund2Persona, a framework that grounds financial-advisor personas in fund disclosures, holdings transitions, market context, and manager commentary, then refines them through an agentic actor--scorer--patcher loop. We evaluate the resulting personas on held-out holdings-transition reconstruction and manager-commentary alignment, where they better recover portfolio decisions and grounded manager interpretation than generic baselines. We further study two downstream diagnostics: market-scenario generation, where persona retrieval broadens plausible investment views beyond repeated generic rollouts, and advisory dialogues grounded in investor profiles, where matched personas give more specific and useful advice than a generic advisor. These results suggest that fund-data-grounded financial-advisor personas can make manager-specific investment expertise portable rather than merely changing an LLM's surface style.