Estimating Loss Given Default by Mixture Beta Distribution Model

Although beta distribution models are a well-known tool for evaluating the recovery risk of credit instruments, concerns are raised regarding tractability its analysis and simulation. The project attempts to address such concerns by incorporating a mixture beta distribution model. The project will compare the efficiency of the proposed model with the commonly used beta distribution model. In addition, the intern will compare the mixture beta distribution model with the credit risk model that is currently employed by Sun Life Financial. Finally, the undertaken work may recommend ways of enhancing the internal quantitative techniques of Sun Life Financial that would allow more accurate and reliable assessment of credit risk.

Yuchuan Jin
Faculty Supervisor: 
Peter Miu
Partner University: