A hierarchical clustering based global outlier detection method
Binmei Liang · 2010
The existance of outlier always leads to inaccurate, even wrong results in data mining. An effective and global outlier detection method is proposed in this paper. Agglomerative hierarchical clustering is performed firstly, and then the outliers is identified unsupervisely from the top to down of the clustering tree. Experimental results show that, the method can effectively detect global outliers, and the algorithm is efficient, user-friendly, and applicable to detect the outliers before data mining for high-dimensional and large databases.