%0 Conference Paper %1 Knorr98algorithmsfor %A Knorr, Edwin M. %A Ng, Raymond T. %D 1998 %K based detection distance outlier %P 392--403 %T Algorithms for Mining Distance-Based Outliers in Large Datasets %U http://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=9A0ED8BD4E41A9DC15F6E02185FD3B8D?doi=10.1.1.55.8026&rep=rep1&type=pdf %X This paper deals with finding outliers (exceptions) in large, multidimensional datasets. The identification of outliers can lead to the discovery of truly unexpected knowledge in areas such as electronic commerce, credit card fraud, and even the analysis of performance statistics of professional athletes. Existing methods that we have seen for finding outliers in large datasets can only deal efficiently with two dimensions/attributes of a dataset. Here, we study the notion of DB- (Distance- Based) outliers. While we provide formal and empirical evidence showing the usefulness of DB-outliers, we focus on the development of algorithms for computing such outliers. First, we present two simple algorithms, both having a complexity of O(k N 2 ), k being the dimensionality and N being the number of objects in the dataset. These algorithms readily support datasets with many more than two attributes. Second, we present an optimized cell-based algorithm that has a complexity that is linear w...

@inproceedings{Knorr98algorithmsfor, abstract = {This paper deals with finding outliers (exceptions) in large, multidimensional datasets. The identification of outliers can lead to the discovery of truly unexpected knowledge in areas such as electronic commerce, credit card fraud, and even the analysis of performance statistics of professional athletes. Existing methods that we have seen for finding outliers in large datasets can only deal efficiently with two dimensions/attributes of a dataset. Here, we study the notion of DB- (Distance- Based) outliers. While we provide formal and empirical evidence showing the usefulness of DB-outliers, we focus on the development of algorithms for computing such outliers. First, we present two simple algorithms, both having a complexity of O(k N 2 ), k being the dimensionality and N being the number of objects in the dataset. These algorithms readily support datasets with many more than two attributes. Second, we present an optimized cell-based algorithm that has a complexity that is linear w...}, added-at = {2010-09-15T09:37:33.000+0200}, author = {Knorr, Edwin M. and Ng, Raymond T.}, biburl = {https://www.bibsonomy.org/bibtex/2467f693edf81f24df46398cb601a8200/michaelkamp}, description = {CiteSeerX — Algorithms for Mining Distance-Based Outliers in Large Datasets}, interhash = {14ec3994be4f136b51ed63d450933f54}, intrahash = {467f693edf81f24df46398cb601a8200}, keywords = {based detection distance outlier}, pages = {392--403}, timestamp = {2010-09-15T09:37:33.000+0200}, title = {Algorithms for Mining Distance-Based Outliers in Large Datasets}, url = {http://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=9A0ED8BD4E41A9DC15F6E02185FD3B8D?doi=10.1.1.55.8026&rep=rep1&type=pdf}, year = 1998 }