Incomplete Data Decomposition for Classification

Rafal Latkowski

Institute of Computer Science, Warsaw University
ul. Banacha 2, 02-097 Warsaw, Poland
rlatkows@mimuw.edu.pl

Abstract

In this paper we present a method of data decomposition to avoid the
necessity of reasoning on data with missing attribute values. The
original incomplete data is decomposed into data subsets without
missing values. Next, methods for classifier induction are applied to
such sets. Finally, a conflict resolving method is used to combine
partial answers from classifiers to obtain final classification. We
provide an empirical evaluation of the decomposition method with use
of various decomposition criteria.