Abstract
Purpose- The main purpose of this article is to make a comprehensive review of existing studies on prepayment and default (competing risk). This review enables to shed light on the main determinant of prepayment and default as well as on methods used to model competing risk. Methodology- A comprehensive review of existing studies/articles. Findings- More recently proposed machine learning methods (Random Survival Forest and Random Competing Risks Forests, as well as the DeepHit model and Dynamic DeepHit model) enable to take into account the complex/no-linear response of prepayment and default to their determinant more efficiently. Conclusion- To model properly/correctly the prepayment and default risks it is important to consider the fact that the exercise of the prepayment option brings an end to the default option, and vice versa. These both risks should be modelled together: competing risk. Furthermore, models/methods accounting the complex/no-linear impact of explanatory variables on prepayment and default risks should be used; such as the Random Survival Forest and Random Competing Risks Forests, as well as the DeepHit model and Dynamic DeepHit model.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
