Optimal Portfolio Diversification via Independent Component Analysis

Operations Research, 2022, 70(1):55-72

56 Pages Posted: 9 Dec 2018 Last revised: 8 Feb 2022

See all articles by Nathan Lassance

Nathan Lassance

LFIN/LIDAM, UCLouvain

Victor DeMiguel

London Business School

Frédéric D. Vrins

LFIN/LIDAM, UCLouvain

Date Written: April 7, 2021

Abstract

A natural approach to enhance portfolio diversification is to rely on factor-risk parity, which yields the portfolio whose risk is equally spread among a set of uncorrelated factors. The standard choice is to take the variance as risk measure, and the principal components (PCs) of asset returns as factors. Although PCs are unique and useful for dimension reduction, they are an arbitrary choice: any rotation of the PCs results in uncorrelated factors. This is problematic because we demonstrate that any portfolio is a factor-variance-parity portfolio for some rotation of the PCs. More importantly, choosing the PCs does not account for the higher moments of asset returns. To overcome these issues, we propose to use the independent components (ICs) as factors, which are the rotation of the PCs that are maximally independent, and care about higher moments of asset returns. We demonstrate that using the IC-variance-parity portfolio helps to reduce the return kurtosis. We also show how to exploit the near independence of the ICs to parsimoniously estimate the factor-risk-parity portfolio based on Value-at-Risk. Finally, we empirically demonstrate that portfolios based on ICs outperform those based on PCs, and several state-of-the-art benchmarks.

Keywords: Portfolio selection, risk parity, factor analysis, principal component analysis, higher moments

JEL Classification: G11

Suggested Citation

Lassance, Nathan and DeMiguel, Victor and Vrins, Frederic Daniel, Optimal Portfolio Diversification via Independent Component Analysis (April 7, 2021). Operations Research, 2022, 70(1):55-72, Available at SSRN: https://ssrn.com/abstract=3285156 or http://dx.doi.org/10.2139/ssrn.3285156

Nathan Lassance (Contact Author)

LFIN/LIDAM, UCLouvain ( email )

151 Chaussée de Binche
Mons, 7000
Belgium

Victor DeMiguel

London Business School ( email )

Sussex Place
Regent's Park
London, London NW1 4SA
United Kingdom

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
1,259
Abstract Views
4,215
Rank
32,331
PlumX Metrics