| 基于SVM和粗糙集理论的董事会效率评价研究 |
| |
| 引用本文： | 张大光.基于SVM和粗糙集理论的董事会效率评价研究[J].中国软科学,2011(9). |
| |
| 作者姓名： | 张大光 |
| |
| 作者单位： | 北京航空航天大学经济管理学院,北京,100191 |
| |
| 摘 要： | 本文构建了影响董事会效率的指标体系,并首次采用支持向量机方法(SVM)建立了董事会效率评价的五级分类模型,通过粗糙集理论的属性约简方法来确定最优的输入指标组合.实验结果表明,本文建立的董事会效率评价模型的判别精度要优于已有模型,而通过对惩罚矩阵的合理调整,模型的判别精度可以进一步提高.
|
| 关 键 词： | 董事会效率 多分类 支持向量机 粗糙集 指标选择 |
Research on Board Effectiveness Evaluation Based on SVM and Rough Set Theory |
| |
| ZHANG Da-guang.Research on Board Effectiveness Evaluation Based on SVM and Rough Set Theory[J].China Soft Science,2011(9). |
| |
| Authors: | ZHANG Da-guang |
| |
| Institution: | ZHANG Da-guang(School of Economics and Management,Beihang University,Beijing 100191,China) |
| |
| Abstract: | This paper builds the indicator system which influences the board effectiveness and composes a five-category SVM model.Then we obtain the optimal input indicator portfolio by the attribute reduction method of rough set theory.The empirical results show that the discrimination accuracy of the proposed model is significantly better than the existed methods;furthermore,the discrimination accuracy can be further improved by the reasonable adjustment of the penalty matrix. |
| |
| Keywords: | board effectiveness multi-category support vector machine rough set indicators selection |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
