Using Entropy to Impute Missing Data in a Classification Task

Thomas Delavallade (1) , Thanh Ha Dang (1)

1 MALIRE - Machine Learning and Information Retrieval

In real applications, part of the data is usually missing. But most techniques of data analysis and data mining can only deal with complete data. In this paper, a new taxonomy of imputation methods is proposed. Within this taxonomy a new technique, based on entropy measures is introduced. Its behaviour is studied through an empirical comparative analysis.

Domaines: Informatique [cs]

Thomas Delavallade, Thanh Ha Dang. Using Entropy to Impute Missing Data in a Classification Task. IEEE International Conference on Fuzzy Systems (Fuzz-IEEE), Jul 2007, London, United Kingdom. pp.577-582, ⟨10.1109/FUZZY.2007.4295430⟩. ⟨hal-01306267⟩