Uncertain Risk Parity

Shah A (2021) Uncertain risk parity. Journal of Investment Strategies 10(1), https://doi.org/10.21314/JOIS.2021.009

6 Pages Posted: 24 Jun 2019 Last revised: 28 Jun 2021

See all articles by Anish Shah

Anish Shah

Investment Grade Modeling; Brown University - Division of Applied Mathematics

Multiple version iconThere are 2 versions of this paper

Date Written: June 18, 2019


Risk parity is a portfolio construction technique that scales sections of a portfolio-e.g., stocks, bonds, currencies, commodities-so that forecasted contributions to net portfolio risk match the budget. Because risks are measured from a point-estimate of covariance, the method is subject to problems of estimation error. This paper treats covariance as uncertain in order to find a risk parity weighting that doesn't count on perfectly optimized hedges and is robust to changes in regime.

Separately, of general interest are the uncertain risk contributions calculated en route. Reporting a portfolio's uncertain risk decomposition puts a band around numbers and reveals fragility. For example, market could seem hedged in a long-short portfolio but surface as the biggest risk when parameters are considered across their error range.

Keywords: Covariance, Estimation Error, Factor Models, Portfolio Construction, Regularization, Risk Parity, Uncertainty

JEL Classification: G11, C44, C61

Suggested Citation

Shah, Anish, Uncertain Risk Parity (June 18, 2019). Shah A (2021) Uncertain risk parity. Journal of Investment Strategies 10(1), https://doi.org/10.21314/JOIS.2021.009, Available at SSRN: https://ssrn.com/abstract=3406321 or http://dx.doi.org/10.2139/ssrn.3406321

Anish Shah (Contact Author)

Investment Grade Modeling ( email )

Cambridge, MA 02139
United States

HOME PAGE: http://www.linkedin.com/in/anishrshah

Brown University - Division of Applied Mathematics

182 George St
Providence, RI 02912
United States

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

Paper statistics

Abstract Views
PlumX Metrics