Classifying Data Having Imbalanced Attribute Using Ensemble Decorate Method

Mining class-imbalanced data is a common yet challenging problem in data mining and machine learning, if the classification categories are not approximately equally represented than database will go in imbalanced state. The distribution of the testing data may different from that of the training data, and the true misclassification costs may be unknown at learning time. So one cannot use classification technique on imbalanced training dataset to found frequent item set else as it may leads to wrong results Predictive accuracy a popular choice for evaluating performance of a classifier, might not be appropriate when the data is Imbalanced. Recently there are many researches are going on how to classify imbalanced data in some balanced form that can be used for generating further result and other research going on designing algorithm to deal with imbalanced real world data. But still a imbalanced data mining is a big issue for data mining and there are worst of research can be done on this area. We used decorate method for balancing data from imbalanced data. In this decorate algorithm we applied rule based classifier for accurate result. So that proposed algorithm work better than existing.