Modeling Credit Risk with Hidden Markov Default Intensity

This paper investigates the modeling of credit default under an interactive reduced-form intensity-based model based on the Hidden Markov setting proposed in Yu et al. (Quant Finance 7(5):781–794, 2017). The intensities of defaults are determined by the hidden economic states which are governed by a Markov chain, as well as the past defaults. We estimate the parameters in the default intensity by using Expectation–Maximization algorithm with real market data under three different practical default models. Applications to pricing of credit default swap (CDS) is also discussed. Numerical experiments are conducted to compare the results under our models with real recession periods in US. The results demonstrate that our model is able to capture the hidden features and simulate credit default risks which are critical in risk management and the extracted hidden economic states are consistent with the real market data. In addition, we take pricing CDS as an example to illustrate the sensitivity analysis.