Classification is one of the most fundamental tasks in the machine learning and data mining communities. One of the most common challenges faced when trying to perform classification is the class imbalance problem. The introduction of class imbalance into the classification problem poses serious and interesting challenges which must be met in order to provide knowledge. An orthogonal problem to class imbalance arises due to concept drift in data streams. Due to the complexity of each of the issues---much less both in tandem---the combination of class imbalance and concept drift are very understudied.In this dissertation we discuss classification in an imbalanced world from a variety of angles. First, we propose methods to overcome class imbalance in its simplest incarnation. In subsequent chapters, we remove restrictions in order to provide novel solutions and insights. By the end of this dissertation, we will present a wide variety of solutions to the class imbalance problem, including the combination of class imbalance and concept drift.Before beginning, however, we present intuitive (and mathematical) definitions of class imbalance and concept drift, as well as an overview of the state of the art methods in each community.