Combining rough sets and rule based classifiers for handling imbalanced data

The paper presents two rough sets based filtering approaches combined with rule based classifiers suited for handling imbalanced data sets, i.e., data sets where the minority class of primary importance is under-represented in comparison to the majority classes. We introduced two techniques to detect and process inconsistent majority cases in the boundary between the minority and majority classes. The experiments showed that the best results were obtained for the relabel filtering, where inconsistent majority examples were reassigned to the minority class, combined with MODLEM rule induction algorithm.