This paper proposes a rating methodology that is based on a non-linear classification method, the support vector machine, and a non-parametric technique for mapping rating scores into probabilities of default. We give an introduction to underlying statistical models and represent the results of...

SFB 649 Discussion Paper 2007-035 Estimating Probabilities of Default With Support Vector Machines Wolfgang Härdle* Rouslan Moro** Dorothea Schäfer*** * Humboldt-Universität zu Berlin, Germany ** Humboldt-Universität zu Berlin & DIW Berlin, Germany *** DIW...

In this master thesis a mechanism to test mononicity of empirical pricing kernels (EPK) is presented. By testing monotonicity of pricing kernel we can determine whether utility function is concave or not. Strictly decreasing pricing kernel corresponds to concave utility function while...