Abstract
This paper presents a new methodology to compute VaR in the portfolio credit loss model. The Wavelet Approximation can be useful to compute non-smooth distributions, often arising in small or concentrated portfolios. We contribute to this technique by extending the Wavelet Approximation for Vasicek one-factor model to multi-factor model. Key features of our new algorithm are: (i) a finite series expansion of the wavelet scaling coefficients, (ii) Wynn's epsilon-algorithm to accelerate convergence of those series, and (iii) an efficient spline interpolation to calculate the Laplace transforms. We illustrate the effectiveness of our algorithm through numerical examples.
