Xiaofeng Zhu, Shichao Zhang, Jilian Zhang, Chengqi Zhang
Various approaches for dealing with missing data have been developed so far. In this paper, two strategies are proposed for cost-sensitive iterative imputing missing values with optimal ordering. Experimental results demonstrate that proposed strategies outperform the existing methods in terms of imputation cost and accuracy.
Subjects: 12. Machine Learning and Discovery; 12. Machine Learning and Discovery
Submitted: Apr 1, 2007