Capital Allocation for Credit Portfolios with Kernel Estimators
by Dirk Tasche of Lloyds Banking Group
Abstract: Determining contributions by sub-portfolios or single exposures to portfolio-wide economic capital for credit risk is an important risk measurement task. Often economic capital is measured as Value-at-Risk (VaR) of the portfolio loss distribution. For many of the credit portfolio risk models used in practice, the VaR contributions then have to be estimated from Monte Carlo samples. In the context of a partly continuous loss distribution (i.e. continuous except for a positive point mass on zero), we investigate how to combine kernel estimation methods with importance sampling to achieve more efficient (i.e. less volatile) estimation of VaR contributions.
Keywords: Capital allocation, kernel estimation, importance sampling.
Published in: Quantitative Finance, Vol. 9, No. 5, (August 2009), pp. 581-595.