Hierarchical Risk Parity (HRP)
A clustering-based allocation method that groups similar assets together and spreads risk between groups, avoiding the matrix instability of mean-variance.
Category: Optimizer & Performance
What is Hierarchical Risk Parity (HRP)?
Proposed by Marcos Lopez de Prado, HRP uses hierarchical clustering on the correlation matrix, then performs recursive bisection so risk is balanced both within and between clusters. It does not require inverting the covariance matrix, making it more robust on noisy data.