| 混合数据特征选择算法及在客户流失预测中的应用 |
| |
| 引用本文： | 周君仪,马少辉.混合数据特征选择算法及在客户流失预测中的应用[J].江苏科技大学学报(社会科学版),2013(6):586-590. |
| |
| 作者姓名： | 周君仪 马少辉 |
| |
| 作者单位： | 江苏科技大学经济管理学院,江苏镇江212003 |
| |
| 基金项目： | 基金项目：江苏省研究生科研创新计划资助项目（CXZZ12-0728） |
| |
| 摘 要： | 特征选择是高维数据处理的一个重要部分，在现实世界中高维的混合数据经常存在。针对高维混合数据，基于模糊粗糙集，在CEBARKNC算法的基础上，改进属性重要性的计算及约简的选取条件，进行特征选择，降低了数据维度，提高了效率，并将其应用于客户流失预测实例中。结果表明：改进的CEBARKNC算法得出的数据用于分类器，与胡清华提出的一个fuzzy-rough算法得出的数据相比，能取得较好的性能。
|
| 关 键 词： | 混合数据 模糊粗糙集 特征选择 客户流失预测 CEBARKNC算法 |
Hybrid data feature selection algorithm and its application in customer churn prediction |
| |
| Zhou Junyi,Ma Shaohui.Hybrid data feature selection algorithm and its application in customer churn prediction[J].Journal of Jiangsu University of Science and Technology:Natural Science Edition,2013(6):586-590. |
| |
| Authors: | Zhou Junyi Ma Shaohui |
| |
| Institution: | (School of Economics and Management, Jiangsu University of Science and Technology, Zhenjiang Jiangsu 212003, China) |
| |
| Abstract: | Feature selection plays an important role in dealing with high-dimensional data .In real-world applica-tions,there usually exist high-dimensional data with hybrid formats , and fuzzy-rough set has been used to deal with these data .In this paper , an improved CEBARKNC algorithm is proposed based on fuzzy-rough set to deal with high-dimensional hybrid data , and attribute importance and selection of feature are improved .The improved algorithm is applied in customer churn prediction .Experiments show that it gets a better performance compared with one fuzzy-rough algorithm proposed by Hu . |
| |
| Keywords: | hybrid data fuzzy-rough set feature selection customer churn prediction CEBARKNC algorithm |
| 本文献已被 维普 等数据库收录！ |
