Handling Unbalanced Data With Smote Adaboost

Abstract

A very important part of data mining is classification techniques, namely how to study a set of data so that rules are generated that can classify or recognize new data that has never been studied. Classification can be defined as a process for declaring a data object as one of the predefined categories (classes). There are many classification techniques global classification techniques have been proposed by experts, which can be grouped into two categories: global classification techniques (taking into account all training data) and local classification techniques (taking into account only part of the training data). each technique has advantages and disadvantages. Some Problems are often encountered in classification, namely the problem of data imbalance. Unbalanced data is a condition where the distribution of data classes is not balanced, the number of one data class is less or more than the number of other data classes. The group of data classes that are less known as the minority group (minority), the other data class group is called the majority group (majority). Classification of data with unbalanced classes is a major problem in the field of data mining, in this research This study resulted in the application of the AdaBoost smote, the AUC value for the Adaboost SMOTE model was 0.784 while the AUC value for the Adaboost model was 0.664.