A data stream is an ordered sequence of instances that in many applications of data stream mining can be read only once or a small number of times using limited computing and storage capabilities.
In many applications, especially operating within non-stationary environments, the distribution underlying the instances or the rules underlying their labeling may change over time, i.e. the goal of the prediction, the class to be predicted or the target value to be predicted, may change over time.
Detecting concept drift is a central issue to data stream mining.
[4][5] Other challenges[6] that arise when applying machine learning to streaming data include: partially and delayed labeled data,[7][8] recovery from concept drifts,[1] and temporal dependencies.
[9] Examples of data streams include computer network traffic, phone conversations, ATM transactions, web searches, and sensor data.