Risk budget portfolios with convex Non-negative Matrix Factorization

TL;DR

This paper introduces a novel portfolio allocation method using convex Nonnegative Matrix Factorization to create interpretable, diversified, long-only portfolios with improved risk profiles, evaluated on cryptocurrency and traditional asset portfolios.

Contribution

The paper presents a new risk budgeting approach based on convex NMF that ensures positive factor loadings and enhances diversification over classical methods.

Findings

Outperforms classical portfolio allocations in diversification

Provides better risk profiles than hierarchical risk parity

Demonstrates robustness through Monte Carlo simulations

Abstract

We propose a portfolio allocation method based on risk factor budgeting using convex Nonnegative Matrix Factorization (NMF). Unlike classical factor analysis, PCA, or ICA, NMF ensures positive factor loadings to obtain interpretable long-only portfolios. As the NMF factors represent separate sources of risk, they have a quasi-diagonal correlation matrix, promoting diversified portfolio allocations. We evaluate our method in the context of volatility targeting on two long-only global portfolios of cryptocurrencies and traditional assets. Our method outperforms classical portfolio allocations regarding diversification and presents a better risk profile than hierarchical risk parity (HRP). We assess the robustness of our findings using Monte Carlo simulation.