This paper presents the top 10 data mining algorithms identified by the IEEE International Conference on Data Mining (ICDM)
December 2006: C4.5, k-Means, SVM, Apriori, EM, PageRank, AdaBoost, kNN, Naive Bayes, and CART. These top 10 algorithms are among the most influential data mining algorithms in the research community.With each algorithm, we provide a description of the algorithm, discuss the impact of the algorithm, and review current andfurther research on the algorithm. These 10 algorithms cover classification, clustering, statistical learning, associationanalysis, and link mining, which are all among the most important topics in data mining research and development.

@article{wu2008wu, author = {Wu, Xindong and Kumar, Vipin and Quinlan, J. Ross and Ghosh, Joydeep and Yang, Qiang and Motoda, Hiroshi and McLachlan, Geoffrey and Ng, Angus and Liu, Bing and Yu, Philip and Zhou, Zhi-Hua and Steinbach, Michael and Hand, David and Steinberg, Dan}, title = {Top 10 algorithms in data mining}, journal = {Knowledge and Information Systems}, publisher = {Springer}, address = {London}, year = {2008}, volume = {14}, number = {1}, pages = {1--37}, url = {http://dx.doi.org/10.1007/s10115-007-0114-2}, issn = {0219-1377}, keywords = {algorithm, ieee, icdm, top, data, mining}, abstract = {This paper presents the top 10 data mining algorithms identified by the IEEE International Conference on Data Mining (ICDM) in December 2006: C4.5, k-Means, SVM, Apriori, EM, PageRank, AdaBoost, kNN, Naive Bayes, and CART. These top 10 algorithms are among the most influential data mining algorithms in the research community.With each algorithm, we provide a description of the algorithm, discuss the impact of the algorithm, and review current andfurther research on the algorithm. These 10 algorithms cover classification, clustering, statistical learning, associationanalysis, and link mining, which are all among the most important topics in data mining research and development.} }

%0 = article %A = Wu, Xindong and Kumar, Vipin and Quinlan, J. Ross and Ghosh, Joydeep and Yang, Qiang and Motoda, Hiroshi and McLachlan, Geoffrey and Ng, Angus and Liu, Bing and Yu, Philip and Zhou, Zhi-Hua and Steinbach, Michael and Hand, David and Steinberg, Dan %C = London %D = 2008 %I = Springer %T = Top 10 algorithms in data mining %U = http://dx.doi.org/10.1007/s10115-007-0114-2

@inproceedings{Steinbach03, author = {Steinbach, Michael and Ertoz, Levent and Kumar, Vipin}, title = {Challenges of Clustering High Dimensional Data}, editor = {Wille, L. T.}, booktitle = {New Vistas in Statistical Physics -- Applications in Econophysics, Bioinformatics, and Pattern Recognition}, publisher = {Springer-Verlag}, year = {2003}, keywords = {challenges, dimensional, clustering, high} }

%0 = inproceedings %A = Steinbach, Michael and Ertoz, Levent and Kumar, Vipin %B = New Vistas in Statistical Physics -- Applications in Econophysics, Bioinformatics, and Pattern Recognition %D = 2003 %I = Springer-Verlag %T = Challenges of Clustering High Dimensional Data

@inproceedings{ertoez02, author = {Ertoz, Levent and Steinbach, Michael and Kumar, Vipin}, title = {A New Shared Nearest Neighbor Clustering Algorithm and its Applications}, booktitle = {Workshop on Clustering High Dimensional Data and its Applications at 2nd SIAM International Conference on Data Mining}, year = {2002}, keywords = {clustering} }

%0 = inproceedings %A = Ertoz, Levent and Steinbach, Michael and Kumar, Vipin %B = Workshop on Clustering High Dimensional Data and its Applications at 2nd SIAM International Conference on Data Mining %D = 2002 %T = A New Shared Nearest Neighbor Clustering Algorithm and its Applications