Risk Analysis Probability of Default : A Stochastic Simulation Model

We present a stochastic simulation model for estimating forward-looking corporate probability of default and loss given default. We formulate the model in a discrete time frame, apply capital-budgeting techniques to define the relationships that identify the default condition, and solve the model by Monte Carlo simulation. First, we present the model; then we show how to extend the model to estimate company specific loss given default, expected loss and unexpected loss as well. Subsequently, we compare the RAPD model with option/contingent models, inasmuch as both models use the same definition of the event of default. The focus of this paper is on the theoretical and modeling aspects of the new methodological approach proposed; however we also present an application of the method that represents just one example of its possible implementations, and the results of a comparative test (covering RAPD, Altman Z-score, two option-contingent models and S&P ratings) which in our opinion constitutes a preliminary positive empirical support of the validity of the RAPD Approach. Conclusive remarks end the paper