采用模糊规划的方法,对模糊不确定环境下的信用风险度量和投资优化问题进行了模型的构建与仿真研究。基于具有自对偶性的可信性测度,提出了模糊条件在险价值作为信用风险度量,并构建了带有投资和收益等约束条件限制的信用风险最小化模型。其中,所考虑市场信用资产预期收益的可能性分布,用指数型模糊变量来刻画。最后,对该信用资产优化模型设计了智能算法,并进行了仿真分析。仿真结果表明,优化后的信用风险明显优于原始的信用风险。
A model for credit risk measurement and portfolio optimization problems under fuzzy uncertainty was established and simulated. Based on self-duality credibility measure, fuzzy conditional value at risk (FCVaR) was proposed as a credit risk measure. A model which can minimize FCVaR subject to trading and return constraints was developed. In this approach, the credit risk possibility distributions of credit assets in considered market are described by exponential fuzzy variables and then the optimization problem is solved effectively with a hybrid intelligent algorithm based on fuzzy simulation method. The simulated results show that the credit risk of optimal portfolio is better than the original porffolio's.