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.