Stream mining was one of three parts of the "Data Mining Algorithms II" Lecture held by Prof. Seidl at RWTH Aachen University: high-dimensional data, stream data and graph data. While not resource (to the best of my knowledge) does cover all discussed algorithms, Gama offers a well-structured introduction to the basics of stream mining. Covered algorithms and concepts - also important for the lecture - are count and sliding window methods (for example counting the number of occurrences or distinct values, or creating a hot-list). Further, change detection, histograms, clustering and decision trees on stream data are discussed.
What is your opinion on this article? Let me know your thoughts on Twitter @davidstutz92 or LinkedIn in/davidstutz92.
Stream mining was one of three parts of the "Data Mining Algorithms II" Lecture held by Prof. Seidl at RWTH Aachen University: high-dimensional data, stream data and graph data. While not resource (to the best of my knowledge) does cover all discussed algorithms, Gama offers a well-structured introduction to the basics of stream mining. Covered algorithms and concepts - also important for the lecture - are count and sliding window methods (for example counting the number of occurrences or distinct values, or creating a hot-list). Further, change detection, histograms, clustering and decision trees on stream data are discussed.