Big data is a popular topic that attracts highly attentions of researchers from all over the world. How to mine valuable information from such huge volumes of data remains an open problem. Although fast development of hardware is capable of handling much larger volume of data than ever before, in the author’s opinion, a well-designed algorithm is crucial in solving the problems associated with big data. Data stream mining methodologies propose one-pass algorithms that discover knowledge hidden behind massive and continuously moving data. These provide a good solution for such big data problems, even for potentially infinite volumes of data. In this paper, we investigate these problems and propose an algorithm of incremental decision tree as the solution.