Imbalanced datasets :Towards a better classification using boosting methods

Abstract

Imbalanced datasets classification is inherently difficult. This situation becomes a challenge when amounts of data are processed to extract knowledge because traditional learning models fail to generate required results due to imbalanced nature of data. In this thesis, we will address the problem of imbalanced datasets whether at the class level, or at the classifier level. In our work, we are interested in binary classification. To do this, we present a set of techniques used to solve this problem in particular boosting methods and machine learning algorithms. Our goal is therefore to rebalance the dataset at the class level and to find an optimal classifier to handle these datasets after balancing. Through the obtained results, it was observed that the boosting methods are well suitable to rebalance the data and thus give a very satisfactory classification result.