Portfolio Construction Based on Implied Correlation Information and VaR

Value at Risk (VaR) is a commonly used downside-risk measure giving the worst case asset-loss over a target horizon for a given confidence level. Today VaR is a mainstay of financial risk management and its relative simplicity ensures its popularity in executive environments. Implied correlation obtained from VaR is effectively an alternative form of the correlation coefficient, in that instead of being calculated based solely on historic performance it takes into account a forecast of worst case loss as well.With the use of three case studies we analyse the effect that implied correlation from VaR has on portfolios of increasing asset size. The case studies start with a minimum risk portfolio and the VaR of each asset concerned is calculated as well as a mean implied correlation, ρ ̄. This implied correlation is then used to adjust the original portfolio's invested fractions in order to view the shift in risk and return. We track comparative portfolios over a 50 day period in order to identify consistent trends between portfolio type and risk encountered. Implied correlation is shown to be a viable method for constructing a portfolio