Fund of Funds (FoF) Construction under the Alliance of PolyModel Theory and Modern Machine Learning Methodologies

Dan Wang, Siqiao Zhao, Zeyu Cao and Raphaël Douady ()
Additional contact information
Raphaël Douady: CES - Centre d'économie de la Sorbonne - UP1 - Université Paris 1 Panthéon-Sorbonne - CNRS - Centre National de la Recherche Scientifique

Université Paris1 Panthéon-Sorbonne (Post-Print and Working Papers) from HAL

Abstract: A fund of funds (FoF) allocates capital across multiple hedge funds, offering diversification, professional management, and access to otherwise unavailable strategies. This article examines how FoF performance can be enhanced using machine learning, PolyModel-based feature selection, and fund size analysis. The authors find that machine learning improves cumulative returns but increases volatility, while PolyModel features—especially long-term stability (LTS)—enhance performance by reducing risk without sacrificing returns. Notably, larger funds do not consistently outperform smaller ones, challenging assumptions about fund scale and reliability. These findings demonstrate that combining interpretable, finance-informed features with advanced analytics supports more robust and disciplined FoF construction.

Keywords: FUNDS-of-funds (Investments); MACHINE learning; PORTFOLIO diversification; RISK management in business; FINANCIAL performance; INVESTMENT policy; RESOURCE allocation (search for similar items in EconPapers)
Date: 2025-10-31
References: Add references at CitEc
Citations:

Published in The Journal of Financial Data Science, 2025, 7 (4), pp.131-150. ⟨10.3905/jfds.2025.1.205⟩

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:cesptp:hal-05611571

DOI: 10.3905/jfds.2025.1.205

Access Statistics for this paper

More papers in Université Paris1 Panthéon-Sorbonne (Post-Print and Working Papers) from HAL
Bibliographic data for series maintained by CCSD ().