关键词: 灰色关联分析法, 特征子集选择, 异常工程检测, 软件缺陷类型预测

Abstract: Grey relational analysis is a method which is always used to describe the degree of influence among the factors and suitable for small project data sets. But the small project data sets often restrain the predicting methods of the traditional software detect types, which causes the inaccuracy and unreliability of the predicting results. This paper particularly proposes feature subset selection method, outlier project detection method, and software defect list prediction method of a project. Moreover it evaluates the approach on publicly available industrial data sets using a series of experiments, and the prediction result demonstrates the method is more accurate and reliable.

Key words: grey relational analysis, feature subset selection, outlier project detection, software defect list prediction