%0 Conference Paper %1 233324 %A Zhang, Tian %A Ramakrishnan, Raghu %A Livny, Miron %B SIGMOD '96: Proceedings of the 1996 ACM SIGMOD international conference on Management of data %C New York, NY, USA %D 1996 %I ACM %K imported %P 103--114 %R http://doi.acm.org/10.1145/233269.233324 %T BIRCH: an efficient data clustering method for very large databases %U http://portal.acm.org/citation.cfm?id=233324&dl=GUIDE&coll=GUID %X Finding useful patterns in large datasets has attracted considerable interest recently, and one of the most widely studied problems in this area is the identification of clusters, or densely populated regions, in a multi-dimensional dataset. Prior work does not adequately address the problem of large datasets and minimization of I/O costs.This paper presents a data clustering method named BIRCH (Balanced Iterative Reducing and Clustering using Hierarchies), and demonstrates that it is especially suitable for very large databases. BIRCH incrementally and dynamically clusters incoming multi-dimensional metric data points to try to produce the best quality clustering with the available resources (i.e., available memory and time constraints). BIRCH can typically find a good clustering with a single scan of the data, and improve the quality further with a few additional scans. BIRCH is also the first clustering algorithm proposed in the database area to handle "noise" (data points that are not part of the underlying pattern) effectively.We evaluate BIRCH's time/space efficiency, data input order sensitivity, and clustering quality through several experiments. We also present a performance comparisons of BIRCH versus CLARANS, a clustering method proposed recently for large datasets, and show that BIRCH is consistently superior. %@ 0-89791-794-4

@inproceedings{233324, abstract = {Finding useful patterns in large datasets has attracted considerable interest recently, and one of the most widely studied problems in this area is the identification of clusters, or densely populated regions, in a multi-dimensional dataset. Prior work does not adequately address the problem of large datasets and minimization of I/O costs.This paper presents a data clustering method named BIRCH (Balanced Iterative Reducing and Clustering using Hierarchies), and demonstrates that it is especially suitable for very large databases. BIRCH incrementally and dynamically clusters incoming multi-dimensional metric data points to try to produce the best quality clustering with the available resources (i.e., available memory and time constraints). BIRCH can typically find a good clustering with a single scan of the data, and improve the quality further with a few additional scans. BIRCH is also the first clustering algorithm proposed in the database area to handle "noise" (data points that are not part of the underlying pattern) effectively.We evaluate BIRCH's time/space efficiency, data input order sensitivity, and clustering quality through several experiments. We also present a performance comparisons of BIRCH versus CLARANS, a clustering method proposed recently for large datasets, and show that BIRCH is consistently superior.}, added-at = {2007-11-08T17:19:28.000+0100}, address = {New York, NY, USA}, author = {Zhang, Tian and Ramakrishnan, Raghu and Livny, Miron}, biburl = {https://www.bibsonomy.org/bibtex/224266b7284daa37d9998c51a9df3eb17/beate}, booktitle = {SIGMOD '96: Proceedings of the 1996 ACM SIGMOD international conference on Management of data}, description = {BIRCH}, doi = {http://doi.acm.org/10.1145/233269.233324}, interhash = {bd3d8e33e8785ecf66408081db016ca4}, intrahash = {24266b7284daa37d9998c51a9df3eb17}, isbn = {0-89791-794-4}, keywords = {imported}, location = {Montreal, Quebec, Canada}, pages = {103--114}, publisher = {ACM}, timestamp = {2008-12-09T16:32:51.000+0100}, title = {BIRCH: an efficient data clustering method for very large databases}, url = {http://portal.acm.org/citation.cfm?id=233324&dl=GUIDE&coll=GUID}, year = 1996 }