The Hierarchical Equal Risk Contribution Portfolio

Abstract

Building upon the fundamental notion of hierarchy, the "Hierarchical Risk Parity" (HRP) and the "Hierarchical Clustering based Asset Allocation" (HCAA), the Hierarchical Equal Risk Contribution Portfolio (HERC) aims at diversifying capital allocation and risk allocation. HERC merges and enhances the machine learning approach of HCAA and the Top-Down recursive bisection of HRP. In more detail, the modified Top-Down recursive division is based on the shape of dendrogram, follows an Equal Risk Contribution allocation and is extended to downside risk measures such as conditional value at risk (CVaR) and Conditional Drawdown at Risk (CDaR). The out-of-sample performances of hierarchical clustering based portfolios are evaluated across two empirical datasets, which differ in terms of number of assets and composition of the universe (multi-assets and individual stocks). Empirical results highlight that HERC Portfolios based on downside risk measures achieve statistically better risk-adjusted performances, especially those based on the CDaR.

Keywords: Hierarchical Clustering, Asset Allocation, Model Confidence Set, Portfolio Construction, Graph Theory, Financial Networks, Machine Learning, Equal Risk Contribution

JEL Classification: G00, G10, G11