基于免疫进化算法的投影寻踪聚类在公司债券财务质量评级中的应用

针对公司债券财务质量评级问题,采用投影寻踪聚类(PPC)模型,将多维数据指标转换到低维子空间,并利用免疫进化算法(IEA)优化其投影方向,根据投影函数值的大小评价出样本的优劣,从而做出决策。应用表明,该方法能利用一个综合反映多因素之间复杂关系的特征指标给出客观而直接的评价结果,且根据计算结果还可以分析各个指标对综合评价结果的影响程度,为公司债券财务质量评级提供了一种计算过程简单、直观的新方法。

Applying PPC Based on IEA in Enterprises Bond Financial Quality Evaluation Grading

This paper evaluates the enterprises bond financial quality according to projection function value through turning multi-dimension data indexes into low-dimension space by using Projection Pursuit Cluster(PPC)model,and meanwhile optimizing its projection direction by Immune Evolutionary Algorithm(IEA).The result shows that the method can construct a characteristic index,and the main impact effects can be analyzed according to the result.The model is qualified with simplicity and can provide a new approach for enterprises bond financial quality evaluation grading.