Parametric Risk Parity

Abstract

Any optimization algorithm based on the risk parity approach requires the formulation of portfolio total risk in terms of marginal contributions. In this paper we use the independence of the underlying factors in the market to derive the centered moments required in the risk decomposition process when the modified versions of Value at Risk and Expected Shortfall are considered. The choice of the Mixed Tempered Stable distribution seems adequate for fitting skewed and heavy tailed distributions. The ensuing detailed description of the optimization procedure is due to the existence of analytical higher order moments. Better results are achieved in terms of out of sample performance and greater diversification.