Abstract
The concept of the data stream has emerged as a result of the evolution of technologies in various fields for instance: banking, electronic commerce, social media, and many others. It represents the sequence of data examples that are generated at a very high speed which can be hard to be stored in memory. Thus, it became hard to extract valuable information from the continuous data stream using traditional data mining. Data Stream Mining DSM algorithms should fulfil some requirements such as limited memory, concept drift detection, and one scan processing. Concept Drift must be tracked to avoid poor performance and inaccurate results of predictive models. It refers to the changing in the data stream distributions due to several reasons including the changes in the environment, individual preferences, or adversary activities. In this paper, we will analyze the classification algorithms handling concept drift for DSM. Also, popular concept drift datasets, data stream tools, and evaluation measures will be presented.