摘要： 文章介绍了金融投资决策中的指标选择方法，提出了一种基于粗集数据分析系统RSDA（Rough Set Data Analysis）的指标子集选择算法。该算法利用信息论的熵函数，根据MDL原理构造评价函数，在全部属性集合中寻找最优属性子集。

关键词: 属性选择, 粗糙集, MDL原理, 机器学习

Abstract: In this paper we introduced a method of feature subset selection in portfolio investment decision system. We also give a feature subset selection algorithm based on RSDA(Rough Set Data Analysis) system. This algorithm uses the concept of entropy and MDLP to define the evaluation function of a feature subset and searches the best feature subset among all features using this function.

中图分类号: 

• TP311