An automatic feature selection system for test data with data (including
the test data and/or the training data containing missing values in order
to improve classifier performance. The missing features for such data are
selected in one of two ways: first approach assumes each missing feature
is uniformly distributed over its range of values whereas in the second
approach, the number of discrete levels for each feature is increased by
one for the missing features. These two choices modify the Bayesian Data
Reduction Algorithm accordingly used for the automatic feature selection.