%0 Report %1 berkhin02survey %A Berkhin, Pavel %C San Jose, CA %D 2002 %K algorithm clustering d4.1 datamining descriptive-learning exploratory-data-analysis hierarchical-clustering imported k-means partitioning probabilistic-clustering review survey tagora unsupervised-learning %T Survey Of Clustering Data Mining Techniques %U citeseer.ist.psu.edu/berkhin02survey.html %X Clustering is a division of data into groups of similar objects. Representing the data by fewer clusters necessarily loses certain fine details, but achieves simplification. It models data by its clusters. Data modeling puts clustering in a historical perspective rooted in mathematics, statistics, and numerical analysis. From a machine learning perspective clusters correspond to hidden patterns, the search for clusters is unsupervised learning, and the resulting system represents a data concept. From a practical perspective clustering plays an outstanding role in data mining applications such as scientific data exploration, information retrieval and text mining, spatial database applications, Web analysis, CRM, marketing, medical diagnostics, computational biology, and many others. Clustering is the subject of active research in several fields such as statistics, pattern recognition, and machine learning. This survey focuses on clustering in data mining. Data mining adds to clustering the complications of very large datasets with very many attributes of different types. This imposes unique computational requirements on relevant clustering algorithms. A variety of algorithms have recently emerged that meet these requirements and were successfully applied to real-life data mining problems. They are subject of the survey.

@techreport{berkhin02survey, abstract = {Clustering is a division of data into groups of similar objects. Representing the data by fewer clusters necessarily loses certain fine details, but achieves simplification. It models data by its clusters. Data modeling puts clustering in a historical perspective rooted in mathematics, statistics, and numerical analysis. From a machine learning perspective clusters correspond to hidden patterns, the search for clusters is unsupervised learning, and the resulting system represents a data concept. From a practical perspective clustering plays an outstanding role in data mining applications such as scientific data exploration, information retrieval and text mining, spatial database applications, Web analysis, CRM, marketing, medical diagnostics, computational biology, and many others. Clustering is the subject of active research in several fields such as statistics, pattern recognition, and machine learning. This survey focuses on clustering in data mining. Data mining adds to clustering the complications of very large datasets with very many attributes of different types. This imposes unique computational requirements on relevant clustering algorithms. A variety of algorithms have recently emerged that meet these requirements and were successfully applied to real-life data mining problems. They are subject of the survey. }, added-at = {2007-03-26T13:52:22.000+0200}, address = {San Jose, CA}, author = {Berkhin, Pavel}, biburl = {https://www.bibsonomy.org/bibtex/22fec60df240f69dbf677e34825d20491/andreab}, description = {Survey Of Clustering Data Mining Techniques - Berkhin (ResearchIndex)}, institution = {Accrue Software}, interhash = {fb9b2c7ce3e0f4e6b579660c40fb67a2}, intrahash = {2fec60df240f69dbf677e34825d20491}, keywords = {algorithm clustering d4.1 datamining descriptive-learning exploratory-data-analysis hierarchical-clustering imported k-means partitioning probabilistic-clustering review survey tagora unsupervised-learning}, timestamp = {2007-03-26T13:52:22.000+0200}, title = {Survey Of Clustering Data Mining Techniques}, url = {citeseer.ist.psu.edu/berkhin02survey.html}, year = 2002 }