Risk Parity Stock Optimization Using Principal Component Quantile Simulation
MetadataShow full item record
Today's portfolio optimization models are often too sensitive to stochasticinput parameters and the use of outdated risk measures, resulting in poorrisk adjusted return. This thesis presents a solution to avoid these dicultiesby introducing a new simulation framework to obtain multivariate returndistributions for correlated assets. Next a model to obtain a risk parityportfolio using Conditional Value at Risk (CVaR) is oered making the modelable to capture asset specic risk characteristics present in the tails of themarginal distributions.Quantile regression and principal component analysis (PCA) are combinedto form a factor model able to capture the entire return distributionand maintain dependencies between correlated assets. A new method tosimulate future principal components is presented making the simulation algorithmquick and eective.The resulting marginal distributions show asset spesic risk characteristicsand tail behaviour. This is in turn reected in the risk parity portfolioweights, conrming CVaR as a risk measure oering better intelligence toinvestors.