摘要
本文在基于行业特性的多元系统风险因子CreditRisk+模型的基础上,对CreditRisk+模型违约损失率假定为一常数这一缺陷进行了修正,提出了一种综合考虑违约损失率变化和行业风险因子相关性的计量贷款组合非预期损失的新方法。该方法进一步提高了计算贷款组合非预期损失的精度。在此基础上,采用鞍点逼近算法进行了算例分析。
On the basis of multi-systematic risk factors CreditRisk ＋ model based on sector character, this paper amended the drawback which the loss given default was assumed to be a constant in the CreditRisk ＋ model, and proposed a new method to calculate the unexpected loss of loan portfolio, which comprehensively considered the variation of loss given default and the correlation of the sector risk factors. We can enhance accuracy when calculating unexpected loss of loan portfolio by this method. In this paper, a practical example was offered to analyze the feasibility of the new method by making use of saddlepoint approximation algorithm.
出处
《预测》
CSSCI
北大核心
2009年第6期48-52,共5页
Forecasting
基金
国家自然科学基金资助项目(70673021)
湖南省研究生科研创新基金资助项目(CX2009B062)
