TITLE:
Evaluating Hierarchical Equal Risk Contribution Portfolios in the Chinese Stock Market
AUTHORS:
Weige Huang, Xiang Gao
KEYWORDS:
Hierarchical Equal Risk Contribution, Machine Learning, Hierarchical Risk Parity, Asset Allocation, Critical Line Algorithm, Inverse-Variance Portfolio
JOURNAL NAME:
Journal of Mathematical Finance,
Vol.12 No.1,
February
21,
2022
ABSTRACT: This paper investigates the usefulness of the Hierarchical Equal Risk Contribution algorithm to exploit correlation structure in China’s equity market over 2001-2020. By running a horse race of different combinations of metrics and linkages, we demonstrate that the winner strategy always beats traditional portfolio construction techniques. Better-performing risk-based hierarchy strategies vary with stock-sorting methods by size, mean return, volatility, and Sharpe ratio. However, our treatment results in extremely imbalanced asset allocation, implying that we capture information other than the standard Chinese industrial classification.