A Modified Hierarchical Risk Parity Framework for Portfolio Management
Journal of Financial Data Science, Forthcoming
Posted: 28 May 2020
Date Written: April 29, 2020
Abstract
This paper introduces a Modified Hierarchical Risk Parity ("MHRP") approach that extends the HRP approach by incorporating three intuitive elements commonly used by practitioners. The new approach (i) replaces the sample covariance matrix with an exponentially weighted covariance matrix with Ledoit-Wolf shrinkage, (ii) improves diversification across portfolio constituents both within and across clusters by relying on an equal volatility, rather than an inverse variance, allocation approach, and (iii) improves diversification across time by applying volatility targeting to portfolios. I examine the impact of the enhancements on portfolios of Commodity Trading Advisors within a large-scale Monte-Carlo simulation framework that accounts for the realistic constraints of institutional investors. I find a striking improvement in the out-of-sample Sharpe ratio of 50%, on average, along with a reduction in downside risk.
Keywords: portfolio management, machine learning, hierarchical risk parity
Suggested Citation: Suggested Citation