论文部分内容阅读
为优化供应链金融多期贷款组合方案,考虑到供应链金融中呈现出的非对称与非线性等典型特征,以分位数回归拟合单个资产边缘分布、以Copula函数刻画资产间非线性关联关系,建立Copula-分位数回归方法。使用该方法,对供应链金融多期贷款收益进行预测,进而通过优化传统Sharpe比率、广义Omega比率等进行贷款组合选择,给出贷款组合优化方案。选取供应链金融中最常见的质押物:现货铝和铜作为研究对象,实证研究发现:第一,依据AIC准则,在Copula-分位数回归方法中,各贷款期限下的t-Copula函数拟合效果均为最优,表明铝和铜之间具有显著的厚尾相关性;第二,在各贷款期限下,Copula-分位数回归方法均优于Copula-GARCH方法,具体表现在前者拥有更高的Sharpe比率和广义Omega比率,能够获得更好的多期贷款组合效果。
In order to optimize the multi-period loan portfolio of supply chain finance, taking into account the typical characteristics of non-symmetry and non-linearity in supply chain finance, the inter-asset non-linear relationship Relationship, the establishment of Copula - quantile regression method. This method is used to predict the return of multi-period loans in supply chain finance, and then the loan portfolio optimization is given by optimizing the traditional Sharpe ratio, generalized Omega ratio and so on. Select the most common collateral in supply chain finance: spot aluminum and copper as the research object. The empirical study found that: First, according to the AIC, in the Copula-quantile regression method, the t-Copula function The results show that both aluminum and copper have a significant thick-tailed correlation. Second, the Copula-quantile regression method is superior to the Copula-GARCH method for each loan term, as indicated by the fact that the former owns A higher Sharpe ratio and a broader Omega ratio will result in better multi-loan portfolios.