Naive Bayes classification based on negative-case-pruning

The traditional data mining algorithms behaves undesirable in the instance of imbalanced data sets, as the distribution of the data sets is not taken into consideration when these algorithms are designed. This paper describes the Naive Bayes classification mechanism, and then points out that, random re-sampling methods not to be able to improve its performance. A negative-case-pruning Naive Bayes (NCP_NB) algorithm is proposed to reduce the negative effects of the class imbalance; Experiments with UCI datasets show the validity of NCP_NB.