Outlier Mining Based on Variance of Angle Technology Research in High-Dimensional Data

Outlier mining in high dimensional data is currently one of the hot areas of data mining. The existing outlier mining methods are based on the distance in the full-dimensional Euclidean space. In high-dimensional data, these methods are bound to deteriorate due to the notorious "dimension disaster" which leads to distance measure can not express the original physical meaning and the low computational efficiency. This paper improves the method of angle-based outlier factor outlier and proposes the method of variance of angle-based outlier factor outlier. It introduces the related theories to guarantee the reliability of the method. The empirical experiments on synthetic data sets show that the method is efficient and scalable to large high-dimensional data sets.