%0 Journal Article %A LIU Caihui %A LIU Dijin %T Survey of Proximity Methods for Outlier Detection %D 2022 %R 10.3778/j.issn.1002-8331.2206-0127 %J Computer Engineering and Applications %P 1-12 %V 58 %N 21 %X Outlier detection is widely used in data mining, but not all outlier detection problems can be solved by an optimal method. For different applications, different methods are used to solve practical problems most effectively. At present, detection methods can be roughly divided into statistics-based, clustering-based, proximity-based(distance-based and density-based) methods. In order to grasp the current research status of outlier detection methods based on proximity technology, through collation and induction, the representative outlier detection methods based on proximity are introduced and evaluated. it is mainly divided into distance-based method and density-based method, and the application scenarios, algorithm ideas, problems that can be solved and their advantages and disadvantages of all the mentioned methods are analyzed and summarized in detail. The existing problems and the development direction of future research are pointed out. It is of great significance to carry out the research of neighborhood outlier detection. %U http://cea.ceaj.org/EN/10.3778/j.issn.1002-8331.2206-0127